Package 'Stat2Data'

Description

Datasets for Stat2: Modeling with Regression and ANOVA (second edition) and Stat2: Building Models for a World of Data (first edition)

Details

This package included datasets for both the first and second editions of the text.

Author(s)

Ann Cannon, George Cobb, Bradley Hartlaub, Julie Legler, Robin Lock, Thomas Moore, Allan Rossman, Jeffrey Witmer

Maintainer: Robin Lock <[email protected]>

Description

Age, price, and mileage of used Honda Accords in 2017

Format

A data frame with 30 observations on the following 3 variables.

Age

Age of used Honda Accord car

Price

Price (in $1,000's)

Mileage

Mileage (in 1,000's of miles)

Details

Information on used Honda Accords obtained from cars.com.

Source

Cars.com, February 2017 using zip code 44107, Lakewood, Ohio

Description

Congressional votes on the American Health Care Act in 2017

Format

A data frame with 430 observations on the following 11 variables.

STATE

State name

Dist

Congressional district

Party

Party affiliation (D=Democrat, R=Republican)

Dem

1=Democrat, 0=Republican

Rep

1=Republican, 0=Democrat

uni2013

Percentage of citizens without health care in 2013

uni2015

Percentage of citizens without health care in 2015

uniChange

uni2015 - uni2013

Member

Name of representative

AHCAvote

1=yes, 0=no

Trump

1=Trump won district, 0=Clinton won district

Details

On May 4, 2017, the U.S. House of Representatives voted, by the narrow margin of 217-213, to pass the American Health Care Act. Most Republicans voted Yes, while all Democrats voted No.

Source

https://fivethirtyeight.com/features/obamacare-has-increased-insurance-coverage-everywhere/

https://docs.google.com/spreadsheets/d/1VfkHtzBTP5gf4jAu8tcVQgsBJ1IDvXEHjuMqYlOgYbA/edit#gid=0

https://www.nytimes.com/interactive/2017/05/04/us/politics/house-vote-republican-health-care-bill.html

Description

Ontime arrivals for American and Delta airlines at LaGuardia and O'Hare airports

Format

A data frame with 10333 observations on the following 5 variables.

airline

American or Delta

airport

LGA=LaGuardia ORD=O'Hare

OnTime

no or yes

IndOHare

Is the airport ORD? (1=yes or 0=no)

IndDelta

Is the airline Delta? (1=yes or 0=no)

Details

Ontime/late data for individual flights to LaGuardia and O'Hare airports by American and Delta airlines.

Source

Data collected on 9/20/16 from http://www.transtats.bts.gov/ot_delay/OT_DelayCause1.asp?pn=1

Description

Growth of alfalfa sprouts in acidic conditions

Format

A dataset with 15 observations on the following 3 variables.

Details

Some students were interested in how an acidic environment might affect the growth of plants. They planted alfalfa seeds in 15 cups and randomly chose five to get plain water, five to get a moderate amount of acid (1.5M HCl), and five to get a stronger acid solution (3.0M HCl). The plants were grown in an indoor room so the students assumed that the distance from the main source of daylight (windows) might have an affect on growth rates. For this reason, they arranged the cups in five rows of three with one cup from each Acid level in each row. These are labeled in the data set as Row: a=farthest from the window through e=nearest to the window.

Source

Neumann, A., Richards, A. L., and Randa, J. (2001). Effects of acid rain on alfalfa plants. Unpublished manuscript, Oberlin College.

Examples

data(Alfalfa)

Description

US Senate party affiliatoin and votes on confirming Samuel Alito for the Supreme Court

Format

A data frame with 100 observations on the following 6 variables.

State

State name

Senator

Senator's name

Party

Party affiliation (D=Democrat, R=Republican)

ConfVote

Confirmation vote (Nay=against or Yea=for)

StateOpinion

Percentage of state residents supporting the choice

Vote

1=for or 0=against

Details

Data from the U.S. Senate vote on January 31, 2006 to confirm Samuel Alito to a position on the Supreme Court.

Source

These numbers are taken from Kastellec, J.P., Lax, J.R., and Phillips, J. (2010), "Public Opinion and Senate Confirmation of Supreme Court Nominees," Journal of Politics, 72(3): 767-84. In this paper the authors used opinion polls and an advanced statistical method known as multilevel regression and poststratification to determine the StateOpinion levels.

Description

Amyloid-beta and cognitive impairment for a sample of Catholic priests

Format

A data frame with 57 observations on the following 2 variables.

Group

mAD=Alzheimer's, MCI=mild impairment, NCI=no impairment

Abeta

Amount of Abeta from the posterior cingulate cortex (pmol/g tissue)

Details

Amyloid-beta (Abeta) is a protein fragment that has been linked to Alzheimer's disease. Autopsies from a sample of Catholic priests included measurements of Abeta (pmol/g tissue from the posterior cingulate cortex) from three groups: subjects who had exhibited no cognitive impairment before death, subjects who had exhibited mild cognitive impairment, and subjects who had mild to moderate Alzheimer's disease.

Source

Violetta N. Pivtoraiko, Eric E. Abrahamson, Sue E. Leurgans, Steven T. DeKosky, Elliott J. Mufson,, Milos D. Ikonomovic (2015) Cortical pyroglutamate amyloid-beta levels and cognitive decline in Alzheimer's disease. Neurobiology of Aging (36) 12-19. Data are read from Figure 1, panel d.

Description

Daily prices and trading volume of Apple stock from July 21st to August 21st in 2016

Format

A data frame with 66 observations on the following 4 variables.

Date

Date as mm/dd/yyyy

Price

Closing price of Apple stock

Change

Change in price from previous day

Volume

Number of shares traded (in millions)

Details

Closing price of Apple stock (AAPL) for each trading day in a three month period from 7/21/2016 to 10/21/2016 as well as the change in stock price and number of shares traded.

Source

Data downloaded from Nasdaq historical prices at http://www.nasdaq.com/symbol/aapl/historical

Description

Score results from an archery class

Format

A dataset with 18 observations on the following 7 variables.

Details

In 2002, Heather Tollerud, a Saint Olaf College student, undertook a study of the archery scores of students at the college who were enrolled in an archery course. Students taking the course record a score for each day they attend class from the first until the last day. Hopefully the instruction they receive helps them to improve their game.

Source

Student project

Description

Six-year graduation data for 214,555 students in 2004

Format

A data frame with 214555 observations on the following 3 variables.

Student

Athlete or NonAthlete

Race

Black or White

Grad

1=graduated within 6 years, otherwise 0

Details

Six-year graduation data from 2004 for male non-athletes and for male athletes, where "Athlete"" means football or basketball player. These data show Simpson's Paradox.

Source

Victor Matheson, College of the Holy Cross, collected the summary statistics.

Data are derived from the summary tables in:

Matheson, V., "Research Note: Athletic Graduation Rates and Simpson's Paradox," Economics of Education Review, Vol. 26:4 (August 2007), 516-520.

Description

Data from an experiment on reaction times to audio or visual stimuli by Oberlin College students.

Format

A data frame with 72 observations on the following 4 variables.

Subject

SubjectIDs coded s1 to s36

ResponseTime

Time to respond to a stimulus (in ms)

Stimulus

Type of stimulus (auditory or visual)

Group

Musician or NonMusician

Details

Subjects in a reaction time study were asked to press a button as fast as possible after being exposed to either an auditory stimulus (a burst of white noise) or a visual stimulus (a circle flashing on a computer screen). Average reaction times (ms) were recorded for between 10 and 20 trials for each type of stimulus for each subject. Data also identifies which subjects are musicians.

Source

Arjuna Pettit, Jr. and Jeremy Potterfield at Oberlin College

Description

Measurements of noise levels for different filters to reduce pollution levels of automobiles.

Format

A dataset with 36 observations on the following 4 variables.

Details

In a 1973 testimony before the Air and Water Pollution Subcommittee of the Senate Public Works Committee, John McKinley, President of Texaco discussed a new filter that had been developed to reduce pollution. Questions were raised about the effects of this filter on other measures of vehicle performance. The data set AutoPollution gives the results of an experiment on 36 different cars. The cars were randomly assigned to get either this new filter or a standard filter and the noise level for each car was measured.

Source

Data explanation and link can be found at http://lib.stat.cmu.edu/DASL/Stories/airpollutionfilters.html.

References

A.Y. Lewin and M.F. Shakun, Policy Sciences: Methodology and Cases, Pergammon Press, 1976, p 313.

Description

Backpack weights for a sample of college students

Format

A data frame with 100 observations on the following 9 variables.

Details

A survey of students at California Polytechnic State University (San Luis Obispo) collected data to investigate the question of whether back aches might be due to carrying heavy backpacks,

Source

Mintz J., Mintz J., Moore K., and Schuh K., "Oh, My Aching Back! A Statistical Analysis of Backpack Weights," Stats: The Magazine for Students of Statistics, vol. 32, 2002, pp. 1719.

Description

Game times and boxscore information for baseball games

Format

A data frame with 15 observations on the following 7 variables.

Details

Data were collected for 15 Major League Baseball (MLB) games played on August 26, 2008.

This dataset was used in first edition, but updated to BaseballTimes2017 for the second edition.

Source

Data from boxscores at www.baseball-reference.com

Description

Times for one day's major league baseball games

Format

A data frame with 14 observations on the following 7 variables.

Game

MLB teams that played

League

AL=American League, IL=Interleague, or NL=National League

Runs

Runs scored by the two teams combined

Margin

Winning margin

Pitchers

Number of pitchers used total for two teams

Attendance

Announced attendance

Time

Time in minutes to play the game

Details

Data from all MLB games played on August 11, 2017. There were no extra-innings game nor any rain delays.

Source

https://www.baseball-reference.com/boxes/?month=8&day=11&year=2017

Description

Data from an experiment to see it the number of bee stings depends on previous stings.

Format

A data frame with 18 observations on the following 3 variables.

Details

If you are stung by a bee, does that make you more likely to get stung again? Might bees leave behind a chemical message that tells other bees to attack you? To test this hypothesis, scientists dangled a 4x4 array of 16 muslin-wrapped cotton balls over a beehive. Eight of 16 balls had been previously stung; the other eight were fresh. The response was the total number of new stingers left behind by the bees. The process was repeated for a total of nine trials.

Used in first edition, but not second edition.

Source

Free, J.B. (1961) "The stinging response of honeybees," Animal Behavior, Vol. 9, pp 193-196.

Description

An experiment on the effects of a hormone on blood calcium levels in robins

Format

A data frame with 20 observations on the following 5 variables.

Bird

ID number for each bird (1 to 20)

Sex

female or male

Hormone

Treated with hormone (no or yes)

Group

Combined Sex and Hormone (F No, F Yes, M No, or M Yes)

Ca

Blood calcium level (mg per 100 ml)

Details

An experiment looked at the effects of treatment with a hormone for increasing the concentration of calcium in birds. Twenty birds (robins) were used in the study, ten male and ten female, equally divided between the hormone and no hormone treatments.

Source

Bliss, Chester (1970), Statistics in Biology, McGraw-Hill

Description

Nest and species characteristics for North American passerines

Format

A data frame with 84 observations on the following 12 variables.

Details

Amy R. Moore, as a student at Grinnell College in 1999, wanted to study the relationship between species characteristics and the type of nest a bird builds, using data collected from available sources. For the study, she collected data by species for 84 separate species of North American passerines.

Source

Project by Amy Moore at Grinnell College

References

The Birders Handbook, by Ehrlich, et al. (1988)

Description

Systolic blood pressure, weight and smoking status for a sample of 500 adults

Format

A data frame with 500 observations on the following 3 variables.

Details

Data on systolic blood pressure, along with smoker status and weight status, for a sample of 500 adults.

Source

Data are part of a larger case study for the 2003 Annual Meeting of the Statistical Society of Canada.
http://www.ssc.ca/en/education/archived-case-studies/case-studies-for-the-2003-annual-meeting-blood-pressure.

Description

Body measurements for a sample of blue jays

Format

A data frame with 123 observations on the following 9 variables.

Details

Body measurements for captured blue jays. Values are averaged for birds captured more than once.

Source

Data from Keith Tarvin, Department of Biology, Oberlin College

Description

Brain tissue pH at time of death

Format

A data frame with 54 observations on the following 5 variables.

pH

Brain tissue pH

Sex

F or M

Ethnicity

AfricanAmerican, Asian, Caucasian, or PacificIslander

Age

Age at death

DeathType

Cause of death (Cardiac, Other, or Suicide)

Details

These are data from a PNAS article (supplemental file) on pH in brain tissue samples for controls and for people who had Major Depressive Disorder. We extracted just the controls (roughly 3/4 of whom died of cardiac arrest).

Source

Jun Z. Li et al. (2013), "Circadian patterns of gene expression in the human brain and disruption in major depressive disorder," PNAS, vol 110, no. 24, www.pnas.org/cgi/doi/10.1073/pnas.1305814110

Data extracted from Supporting Information, Table S4: Li et al. www.pnas.org/cgi/content/short/1305814110

Description

Passing statistics for football quarterback Drew Brees in 2016

Format

A data frame with 16 observations on the following 5 variables.

Game

Game number (1 is the first game of the regular season)

Opponent

Opponent abbreviation

Completed

Number of completed passes

Attempts

Pass attempts

Yards

Passing yards

Details

Drew Brees was the quarterback for the NFL's New Orleans Saints football team in 2016. This dataset shows some of his passing statistics for each of the 16 regular season games.

Source

http://www.espn.com/nfl/player/gamelog/_/id/2580/year/2016

Description

Poll attitudes towards British trade unions

Format

A data frame with 17 observations on the following 7 variables.

Details

The British polling company Ipsos MORI conducted several opinion polls in the UK between 1975 and 1995 in which they asked whether people agree or disagree with the statement "Trade unions have too much power in Britain today".

Source

Data from the Ipsos MORI website at
http://www.ipsos-mori.com/researchpublications/researcharchive/poll.aspx?oItemID=94

Description

Measurements for a sample of butterflies in Greenland

Format

A data frame with 32 observations on the following 4 variables.

Temp

Average temperature for preceding summer (Celsius)

Wing

Average wing length (mm)

Sex

Female or Male

Species

all are Bc, Boloria chariclea

Details

Scientists measured wing length of a species of butterfly, Boloria chariclea (Bc), in Greenland each year from 1996 through 2013. They also recorded summer temperatures.

Source

Digitized data from plots in Bowden, J. et al., "High-Arctic butterflies become smaller with rising temperatures", published in Biology Letters 11: 20150574

Description

Senate votes for Corporate Average Fuel Economy (CAFE) bill

Format

A data frame with 100 observations on the following 7 variables.

Details

The Corporate Average Fuel Economy (CAFE) Bill was proposed by Senators John McCain and John Kerry to improve the fuel economy of cars and light trucks sold in the United States. However a critical vote on an amendment in March of 2002 threatened to indefinitely postpone CAFE. The amendment charged the National Highway Traffic Safety Administration to develop a new standard, the effect being to put on indefinite hold the McCain-Kerry bill. It passed by a vote of 62-38. A political question of interest is whether there is evidence of monetary influence on a senator's vote. Scott Preston, a professor of statistics at SUNY, Oswego, collected data on this vote which includes the vote of each senator (1=Yes or 0=No) and monetary contributions that each of the 100 senators received over his or her lifetime from the car manufacturers.

Source

Thanks to Prof. Scott Preston from SUNY Oswego for the data.

Description

An experiment on calcium supplements and blood pressure in 21 men

Format

A data frame with 21 observations on the following 2 variables.

Details

The purpose of this study was to see whether daily calcium supplements can lower blood pressure. The subjects were 21 men; each was randomly assigned either to a treatment group or to a control group. Those in the treatment group took a daily pill containing calcium. Those in the control group took a daily pill with no active ingredients. Each subject's blood pressure was measured at the beginning of the 12-week study, and again at the end. The decrease in blood pressure (begin-end) was recorded (so a negative value means blood pressure increased).

Source

Dataset downloaded from online data source Data and Story Library,
http://lib.stat.cmu.edu/DASL/Stories/CalciumandBloodPressure.html

Description

US Senate vote on Klobuchar amendment to lower drug prices

Format

A data frame with 94 observations on the following 6 variables.

Senator

Name of the Senator

Contributions

Amount of money received from the pharmaceutical industry over 6 years

Party

D=Democrat or R=Republican

State

Abbreviation for Senator's state

RollCall

Nay or Yea

Vote

Against or With what drug makers wanted

Details

January 2017 vote in the U.S. Senate related to repeal part of ObamaCare. The "Klobuchar amendment" to a bill was introduced with the purpose of lowering drug prices by allowing prescription drugs to be imported from Canada.

The data exclude two senators who did not vote on the amendment and four senators who were new to Congress and thus had received no money from the drug industry. The remaining 94 senators represent 49 states (every state except California) and each of these senators had received at least $3,000.

Source

Data obtained from:

http://www.senate.gov/legislative/LIS/roll_call_lists/roll_call_vote_cfm.cfm?congress=115&session=1&vote=00020

http://maplight.org/us-congress/interest/H4300/view/all

Description

Cancer survival with ascorbate supplement

Format

A dataset with 64 observations on the following 2 variables.

Details

In the 1970's doctors wondered if giving terminal cancer patients a supplement of ascorbate would prolong their lives. They designed an experiment to compare cancer patients who received ascorbate to cancer patients who did not receive the supplement. The result of that experiment was that, in fact, ascorbate did seem to prolong the lives of these patients. But then a second question arose. Was the effect of the ascorbate different when different organs were affected by the cancer? The researchers took a second look at the data. This time they concentrated only on those patients who received the ascorbate and divided the data up by which organ was affected by the cancer. They had 5 different organs represented among the patients (all of whom only had one organ affected): Stomach, bronchus, colon, ovary, and breast.

Source

From the article "Supplemental Ascorbate in the Supportive Treatment of Cancer: Reevaluation of Prolongation of Survival Times in Terminal Human Cancer" by Ewan Cameron and Linus Pauling, Proceedings of the National Academy of Sciences of the United States of America, Vol. 75, No. 9 (Sep., 1978), pp. 4538-4542.

Description

Measurements on a sample of Manduca Sexta caterpillars

Format

A data frame with 267 observations on the following 18 variables.

Details

Student and faculty researchers at Kenyon College conducted numerous experiments with Manduca Sexta caterpillars to study biological growth.

Source

We thank Professors Harry Itagaki, Drew Kerkhoff, Chris Gillen, and Judy Holdener and their students for sharing this data from research supported by NSF InSTaRs grant #0827208.

Description

Shooting percentages for two Cav players

Format

A data frame with 1940 observations on the following 3 variables.

Player

Frye or Irving

ShotType

Two or Three

Hit

1=made or 0=missed

Details

Shooting success on 2-point shots and 3-point shots for the 2016-17 NBA season for two Cleveland Cavalier basketball players, Kyrie Irving and Channing Frye. Each case is a shot attempt. These data show Simpson's Paradox.

Source

http://www.espn.com/nba/player/splits/_/id/6442/kyrie-irving http://www.espn.com/nba/player/splits/_/id/2754/type/total/channing-frye

Description

Nutrition content for a sample of 36 different brands of breakfast cereals

Format

A data frame with 36 observations on the following 4 variables.

Details

Data give nutrition contents (per serving) for 36 breakfast cereals.

Source

These data were collected by Patricia Benedict, Ronald Brahler, and Kenneth Motz, who read the nutritional labels on the boxes, in an attempt to learn whether cereals high in fiber are also high in sugar and calories. The cereals are all of those that were sold at Russo Stop & Shop in University Heights, OH, in July, 1990.

Description

Comparison of two treatments for nausea in chemotherapy

Format

A data frame with 2 observations on the following 4 variables.

Details

An article in the New England Journal of Medicine described a study on the effectiveness of medications for combatting nausea in patients undergoing chemotherapy treatments for cancer. In the experiment, 157 patients were divided at random into two groups. One group of 78 patients was given a standard antinausea drug called prochlorperazine, while the other group of 79 patients received THC (the active ingredient in marijuana). Both medications were delivered orally and no patients were told which of the two drugs they were taking. The response measured was whether or not the patient experienced relief from nausea when undergoing chemotherapy. Dataset is a 2 x 2 table of counts.

Source

Sallan SE, Cronin C, Zelen M, Zinberg NE (1980), "Antiemetics in patients receiving chemotherapy for cancer: a randomized comparison of delta-9-tetrahydrocannabinol and prochlorperazine," New England Journal of Medicine, 302(3) p.135-138.

Description

Age at first speaking and aptitude test scores

Format

A data frame with 21 observations on the following 3 variables.

Details

The data are from a study about whether there is a relationship between the age at which a child first speaks (in months) and his or her score on a Gesell Aptitude Test taken later in childhood.

Source

These data were originally collected by L.M. Linde of UCLA but were first published by M.R. Mickey, O.J. Dunn, and V. Clark, "Note on the use of stepwise regression in detecting outliers," Computers and Biomedical Research, 1 (1967), pp. 105-111. The data have been used by several authors. We found them in David Moore's Basic Practice of Statistics, WH Freeman (2004)

Description

2016 US Democratic Presidential primary results

Format

A data frame with 31 observations on the following 5 variables.

State

ID for primary state

Delegates

Percentage of delegates won by Clinton

PaperTrail

Was a paper trail available for votes cast? (No Paper Trail or Paper Trail)

PopularVote

Percentage of votes won by Clinton

AfAmPercent

Percentage of African-Americans in the state

Details

In 2016 Hillary Clinton won the Democratic nomination for U.S. President over Bernie Sanders. A paper was circulated that claimed to show evidence of election fraud based, among other things, on Clinton doing better in states that don't have a paper trail for votes cast in a primary election than she did in states that have a paper trail. Data is for the 31 states that held Democratic primaries in 2016.

Source

https://docs.google.com/spreadsheets/d/1cszGOhbmHDTHH5ntaGPmeX55RgMMaoBhgqO1Wx-9TRk/ edit#gid=0

http://kff.org/other/state-indicator/distribution-by-raceethnicity/ ?currentTimeframe=0&sortModel=%7B%22colId%22:%22Location%22,%22sort%22:%22asc%22%7D

Description

Data on 60 customers at a clothing retailer

Format

A data frame with 60 observations on the following 8 variables.

Details

This dataset represents a random sample of 60 customers from a large clothing retailer. The manager of the store is interested in predicting how much a customer will spend on his or her next purchase based on one or more of the available explanatory variables.

Source

Personal communication with David Cameron who completed a more extensive consulting project for the retailer.

Description

Rainfall amounts from a cloud seeding experiment (winter only)

Format

A data frame with 28 observations on the following 7 variables.

Details

Researchers were interested in whether seeded clouds would produce more rainfall. An experiment was conducted in Tasmania between 1964 and 1971 and rainfall amounts were measured in inches per rainfall period. The researchers measured the amount of rainfall in two target areas: East (TE) and West (TW). They also measured the amount of rainfall in three control locations. Clouds were coded as being either seeded (treatment) or unseeded (control). This is a subset (only Winter months) of the larger CloudSeeding2 dataset. All rainfall amounts are in inches.

Source

Data were accessed from the website www.statsci.org/data/oz/cloudtas.html. This is the web home of the Australasian Data and Story Library (OzDASL).

References

A.J. Miller, D.E. Shaw, L.G. Veitch, and E.J. Smith, (1979) "Analyzing the results of a cloud-seeding experiment in Tasmania" in Communications in Statistics: Theory and Methods, A8 (10), pp. 1017-1047.

Description

Rainfall amounts from a cloud seeding experiment

Format

A data frame with 108 observations on the following 8 variables.

Details

Researchers were interested in whether seeded clouds would produce more rainfall. An experiment was conducted in Tasmania between 1964 and 1971 and rainfall amounts were measured in inches per rainfall period. The researchers measured the amount of rainfall in two target areas: East (TE) and West (TW). They also measured the amount of rainfall in three control locations. Clouds were coded as being either seeded (treatment) or unseeded (control). A subset (only Winter months) of these data is stored in CloudSeeding. All rainfall amounts are in inches.

Source

Data were accessed from the website www.statsci.org/data/oz/cloudtas.html. This is the web home of the Australasian Data and Story Library (OzDASL).

References

A.J. Miller, D.E. Shaw, L.G. Veitch, and E.J. Smith, (1979) "Analyzing the results of a cloud-seeding experiment in Tasmania" in Communications in Statistics: Theory and Methods, A8 (10), pp. 1017-1047.

Description

Daily carbon dioxide measurements for April through November 2011

Format

A data frame with 237 observations on the following 2 variables.

CO2

Carbon dioxide (CO2) level (in parts per million)

Day

Number of day in 2011 (April 1 = day 91)

Details

Scientists at a research station in Brotjacklriegel, Germany recorded CO2 levels, in parts per million, in the atmosphere for each day from the start of April through November in 2011.

This dataset was renamed to CO2Germany for the second edition.

Source

http://gaw.empa.ch/gawsis/reports.asp?StationID=-739519191

Description

Daily carbon dioxide measurements for April through November 2011

Format

A data frame with 237 observations on the following 2 variables.

CO2

Carbon dioxide (CO2) level (in parts per million)

Day

Number of day in 2011 (April 1 = day 91)

Details

Scientists at a research station in Brotjacklriegel, Germany recorded CO2 levels, in parts per million, in the atmosphere for each day from the start of April through November in 2011.

Source

http://gaw.empa.ch/gawsis/reports.asp?StationID=-739519191

Description

Monthly carbon dioxide readings at Mauna Loa, Hawaii

Format

A data frame with 360 observations on the following 4 variables.

Year

Year (1988 - 2017)

Month

Month (1=Jan. to 12=Dec.)

CO2

Atmospheric carbon dioxide level (ppm)

t

Time interval (t=1 to 360)

Details

Monthly average carbon dioxide readings (1988 - 2017) at the Mauna Loa Observatory in Hawaii. Data collected and disseminated by ERSL (Earth System Research Laboratory) of the U.S. NOAA (National Oceanic and Atmospheric Administration.

Source

Data downloaded for MOL (Mauna Loa) from the ESRL/GMD data page at https://www.esrl.noaa.gov/gmd/ccgg/trends/data.html

Description

Monthly carbon dioxide readings at the South Pole

Format

A data frame with 348 observations on the following 4 variables.

Year

Year (1988 - 2016)

Month

Month (1=Jan. to 12=Dec.)

CO2

Atmospheric carbon dioxide level (ppm)

t

Time interval (t=1 to 348)

Details

Monthly average carbon dioxide readings (1988 - 2016) at the South Pole. Data collected and disseminated by ERSL (Earth System Research Laboratory) of the U.S. NOAA (National Oceanic and Atmospheric Administration.

Source

Data downloaded for SPO (South Pole) from the ESRL/GMD data page at https://www.esrl.noaa.gov/gmd/dv/data/

Description

Drug interaction study with oral contraceptives

Format

A data frame with 44 observations on the following 6 variables.

ID

ID number for each of the women

StudyPeriod

1=first or 2=second

Treatment

Drug or Placebo

EE

Bioavailability of the ethinyl estradiol component of the oral contraceptive (in pg*hr/ml)

ComparisonValues

Comparison values used for a Tukey nonadditivity plot

Residuals

Residuals used for a Tukey nonadditivity plot

Details

Twenty-two female subjects were allocated randomly to one of two treatment sequences in a two period crossover design. The two treatments were a new Drug D or placebo, both given concomitantly with a standard oral contraceptive which was given in both study periods. The oral contraceptive has two components, ethinyl estradiol (EE) and norethindrone (NET). The purpose of the study was to evaluate whether the presence of Drug D affected the bioavailability of each of the oral contraceptive components. Note that our dataset does not include the NET variable.

Source

Thomas E. Bradstreet & Deborah L. Panebianco (2017) "An Oral Contraceptive Drug Interaction Study", Journal of Statistics Education, 12:1, DOI: 10.1080/10691898.2004.11910719

Description

This function produces an plot of standardized residuals versus leverage values for a regression model. Horizontal boundaries identify mild or more extreme standardized residuals. Vertical boundaries identify mild and more severe high leverage points. Curved boundaries identify mild and more severe values of Cook's D.

Usage

cooksplot(mod)

Arguments

Details

The plot shows standardized residuals (vertical) versus leverage values (horizontal) for all cases in a regression model.

Horizontal (blue) boundaries mark standardized residuals beyond +/- 2 (mild) and +/- 3 (more severe).

Vertical (green) boundaries mark leverage points beyond 2(k+1)/4 (mild) and 3(k+1)/n (more severe), where k= number of predictors.

Curved (red) boundaries for mark influential points beyond 0.5 (mild) and 1.0 (more severe) using Cook's D.

Unusual points are labeled with a case number.

Value

A plot showing standardized residuals versus leverage values with boundaries for unusual cases

Examples

data(AccordPrice)
mod1=lm(Price~Age,data=AccordPrice)
cooksplot(mod1)

Description

Medical facilities and doctors in a sample of counties.

Format

A data frame with 53 observations on the following 4 variables.

County

County name, state

MDs

Number of medical doctors

Hospitals

Number of community hospitals

Beds

Number of beds in the hospitals

Details

Data compiled from information provided by the American Medical Association on the availability of health care in counties in the United States. A random sample of 53 counties was chosen from among counties with at least two community hospitals.

Source

Physicians–American Medical Association, Chicago, IL, Physician Characteristics and Distribution in the U.S., annual (copyright), accessed May 17, 2006. Community hospitals–Health Forum LLC, an American Hospital Association (AHA) Company, Chicago, IL, Hospital Statistics, and unpublished data (copyright), e-mail accessed May 4, 2006 (related Internet site http://www.healthforum.com).

Other web sources:
http://www.ama-assn.org/ http://www.healthforum.com/healthforum/html/data_statistics/data_statistics.html http://www.cms.hhs.gov http://www.ssa.gov

Description

Oxygen intake of crabs with different noise sources

Format

A data frame with 34 observations on the following 3 variables.

Mass

Oxygen intake of crabs with different noise sources

Oxygen

Rate of oxygen consumption (mu moles h^-1)

Noise

Source of noise (ambient or ship)

Details

Animals that are stressed might increase their oxygen consumption. Biologists measured oxygen consumption of shore crabs that were either exposed to 7.5 minutes of ship noise or 7.5 minutes of ambient harbor noise.

Source

Wale MA, Simpson SD, Radford AN. (2013) "Size-dependent physiological responses of shore crabs to single and repeated playback of ship noise", Biol Lett 9: 20121194. http://dx.doi.org/10.1098/rsbl.2012.1194

Description

Digested calories with different types of fiber in crackers

Format

A data frame with 48 observations on the following 3 variables.

Details

Twelve female subjects were fed a controlled diet, with crackers before every meal. There were four different kinds of crackers: control, bran fiber, gum fiber, and a combination of both bran and gum fiber. Over the course of the study, each subject ate all four kinds of crackers, one kind at a time, for a stretch of several days. The order was randomized. The response is the number of digested calories, measured as the difference between calories eaten and calories passed through the system.

Source

Subset of the data at http://lib.stat.cmu.edu/DASL/Datafiles/Fiber.html.

Description

Variables that might be related to whether students overdraw a checking account.

Format

A data frame with 450 observations on the following 4 variables.

Details

Researchers conducted a survey of 450 undergraduates in large introductory courses at either Mississippi State University or the University of Mississippi. There were close to 150 questions on the survey, but only four of these variables are included in this dataset. (You can consult the paper to learn how the variables beyond these 4 affect the analysis.) The primary interest for the researchers was factors relating to whether or not a student has ever overdrawn a checking account.

Source

Worthy S.L., Jonkman J.N., Blinn-Pike L. (2010), "Sensation-Seeking, Risk-Taking, and Problematic Financial Behaviors of College Students," Journal of Family and Economic Issues, 31: 161-170

Description

Lengths of cuckoo eggs laid in other birds' nests

Format

A data frame with 120 observations on the following 2 variables.

Details

Cuckoos are knows to lay their eggs in the nests of other (host) birds. The eggs are then adopted and hatched by the host birds. The data give the lengths of cuckoo eggs found in nests of various other bird species.

Source

Downloaded from DASL at http://lib.stat.cmu.edu/DASL/Datafiles/cuckoodat.html

References

"The Egg of Cuculus Canorus. An Enquiry into the Dimensions of the Cuckoo's Egg and the Relation of the Variations to the Size of the Eggs of the Foster-Parent, with Notes on Coloration", by Oswald H. Latter, Biometrika, Vol. 1, No. 2 (Jan., 1902), pp. 164-176.

Description

Data from a first day class survey in an introductory statistics course

Format

A data frame with 43 observations on the following 13 variables.

Details

An instructor at a small liberal arts college distributed a data survey on the first day of class. The data for two different sections of the course are given in this dataset.

Source

Student survey in an introductory statistics class.

Description

The rate of lactic acid turnover was measured by two methods for normal and diabetic dogs.

Format

A data frame with 20 observations on the following 4 variables.

Dog

Code for individual dogs (d1 through d10)

Method

Tracer method to measure response (infuse or inject)

Operation

Pancreas removed to make the dog diabetic? (no or yes)

Response

Rate for biochemical turnover of lactic acid

Details

Five dogs had their pancreas removed to make them diabetic (Operation=yes), the other five were normal (Operation=no). The rate of turnover of lactic acid was measured for each dog by two methods, infusion and injection.

Source

Forbath, N., A. B. Kenshole, and G. Hetenyi, Jr. (1967),"Turnover lactic acid in normal and diabetic dogs calculated by two tracer methods," Am. J. Physiol. v. 212, pp.1179 - 1183.

Description

Price and characteristics for a sample of 351 diamonds

Format

A data frame with 351 observations on the following 6 variables.

Details

Data for a sample of diamonds. The clarity of the diamonds ranges from IF (internally flawless) through VVS1 (very,very slightly included), VS1 (very slightly included), to SI3 (slightly included) in the order listed above.

Source

Diamond data obtained from AwesomeGems.com on July 28, 2005.

Description

A subset of 307 cases with the most frequent colors from the Diamonds data

Format

A data frame with 307 observations on the following 6 variables.

Details

A subset of the Diamonds data, containing only those with most frequent colors D, E, F, and G. The clarity of the diamonds ranges from IF (internally flawless) through VVS1 (very,very slightly included), VS1 (very slightly included), to SI3 (slightly included) in the order listed above.

Source

Diamond data obtained from AwesomeGems.com on July 28, 2005.

Description

Iridium levels in prehistoric rock layers

Format

A data frame with 28 observations on the following 4 variables.

ID

Sample identifier

Source

Type of rock (Limestone Shale)

Depth

Depth of the sample (in meters)

Iridium

Iridium concentration (ppb)

Details

The question of interest is whether a volcanic eruption or asteroid strike had created a dust cloud that led to extinction of most dinosaurs. Rock samples taken in Gubbio, Italy were measured for the concentration of iridium (a rare metal which is more common in asteroids). The deeper the sample, the older the rocks are. A sudden increase in iridium at some point in time would lend support for the asteroid hypothesis.

Source

Ramsey, Fred L. and Daniel W. Schafer (2002). The Statistical Sleuth, 2nd ed., Pacific Grove, CA, Duxbury, pp.405-407.

Description

State-by-state information from the 2008 U.S. presidential election

Format

A dataframe with 51 observations on the following 7 variables.

Details

This dataset contains information from all 50 states and the District of Columbia for the 2008 U.S. presidential election.

Source

State income data from: Census Bureau Table 659. Personal Income Per Capita (in 2007)
High school data from: U.S. Census Bureau, 1990 Census of Population,
http://nces.ed.gov/programs/digest/d08/tables/dt08_011.asp
College data from: Census Bureau Table 225. Educational Attainment by State (in 2007)
% Democrat and %Republican:
http://www.gallup.com/poll/114016/state-states-political-party-affiliation.aspx#1

Description

2016 presidential election and state demographic data

Format

A data frame with 50 observations on the following 8 variables.

State

State name

Abr

Abbreviation for state name

Income

Per capita income in the state

HS

Percent high school grads

BA

Percent college grads

Adv

Percent with advanced degrees

Dem.Rep

Democratic lean - Republican lean in 2015 Gallup poll

TrumpWin

Trump won the state? (1=yes or 0=no)

Details

This dataset contains information from all 50 states and the District of Columbia for the 2016 U.S. presidential election. It is similar to Election08 for the 2008 election.

Source

Income data from
https://www.census.gov/search-results.html?q=per+capita+income+by+state&search.x=0 &search.y=0&search=submit&page=1&stateGeo=none&searchtype=web&cssp=SERP

2015 data via American Community Survey
https://en.wikipedia.org/wiki/List_of_U.S._states_by_educational_attainment from Bureau, U.S. Census. "2011-2015 American Community Survey 5-Year Estimates. factfinder.census.gov. Retrieved 2017-01-19.

http://www.gallup.com/poll/188969/red-states-outnumber-blue-first-time-gallup-tracking.aspx

Description

Age and height of male African elephants

Format

A data frame with 138 observations on the following 3 variables.

Age

Age (in years)

Height

Shoulder height (in cm)

Firstborn

Firstborn? (1=yes, 0=no)

Details

Data on 138 male African elephants that lived through droughts in the first two years of life.

Source

Data are from Phyllis Lee, Stirling University, and are related to Lee, P., et al. (2013), "Enduring consequences of early experiences: 40-year effects on survival and success among African elephants (Loxodonta Africana)," Biology Letters, 9: 20130011.

Description

Age and height of African elephants

Format

A data frame with 288 observations on the following 3 variables.

Age

Age (in years)

Height

Shoulder height (in cm)

Sex

F=female or M=male

Details

Data on 288 African elephants that lived through droughts in the first two years of life.

Source

Data are from Phyllis Lee, Stirling University, and are related to Lee, P., et al. (2013), "Enduring consequences of early experiences: 40-year effects on survival and success among African elephants (Loxodonta Africana)," Biology Letters, 9: 20130011.

Description

This function produces an empirical logit plot for a binary response variable and a single quantitative predictor variable.

Usage

emplogitplot1(formula, data = NULL, ngroups = 3, breaks = NULL,
  yes = NULL, padj = TRUE, out = FALSE, showplot = TRUE,
  showline = TRUE, ylab = "Log(Odds)", xlab = NULL,
  dotcol = "black", linecol = "blue", pch = 16, main = "",
  ylim = NULL, xlim = NULL, lty = 1, lwd = 1, cex = 1)

Arguments

Details

Values of the quantitative explanatory variable will be grouped into ngroups roughly equal sized groups, unless breaks is used to determine the boundaries of the groups. Using ngroups="all" will make each distinct value of the explanatory variable its own group

We find an adjusted proportion for the binary response variable within each of the groups with (Number yes +0.5)/(Number of cases+1). This is converted to an adjusted log odds log(adjp/(1-adjp)). The adjustment avoids problems if there are no "successes" or all "successes" in a group. What constitutes a "success" can be specified with yes= and the proportion adjustment can be turned off (if no group proportions are likely to be zero or one) with padj=FALSE.

The function plots the log odds versus the mean of the explanatory variable within each group. A least square line is fit to these points. The plot can be suppressed with showplot=FALSE.

The out=TRUE option will return a dataframe with the boundaries of each group, proportion, adjusted proportion, mean explanatory variable, and (adjusted or unadjusted) log odds.

Value

A dataframe with group information (if out=TRUE)

Examples

data(MedGPA)
emplogitplot1(Acceptance~GPA,data=MedGPA)

GroupTable=emplogitplot1(Acceptance~MCAT,ngroups=5,out=TRUE,data=MedGPA)

emplogitplot1(Acceptance~MCAT,data=MedGPA,breaks=c(0,34.5,39.5,50.5),dotcol="red",linecol="black")

data(Putts1)
emplogitplot1(Made~Length,data=Putts1,ngroups="all")

Description

This function produces an empirical logit plot for a binary response variable and with a single quantitative predictor variable broken down by a single categorical factor.

Usage

emplogitplot2(formula, data = NULL, ngroups = 3, breaks = NULL,
  yes = NULL, padj = TRUE, out = FALSE, showplot = TRUE,
  showline = TRUE, ylab = "Log(Odds)", xlab = NULL,
  putlegend = "n", levelcol = NULL, pch = NULL, main = "",
  ylim = NULL, xlim = NULL, lty = NULL, lwd = 1, cex = 1)

Arguments

Details

Values of the quantitative explanatory variable will be grouped into ngroups roughly equal sized groups, unless breaks is used to determine the boundaries of the groups. Using ngroups="all" will make each distinct value of the explanatory variable its own group

We find a proportion for the binary response variable within each of the groups created from the quantitative variable crossed with the categrical variable. To avoid problems with proportions of zero and one, we compute an adjusted proportion with (Number yes +0.5)/(Number of cases+1). This is converted to an adjusted log odds log(adjp/(1-adjp)). What constitutes a "success" can be specified with yes= and the proportion adjustment can be turned off (if no group proportions are likely to be zero or one) with padj=FALSE.

The function plots the log odds versus the mean of the explanatory variable within each group with different colors for each of the categories defined by the categorical variable. A least square line is fit to these points within each categorical group. The plot can be suppressed with showplot=FALSE.

The out=TRUE option will return a dataframe with the boundaries of each group, proportion, adjusted proportion, mean explanatory variable, and (adjusted or unadjusted) log odds.

Value

A dataframe with group information (if out=TRUE)

Examples

data(MedGPA)
emplogitplot2(Acceptance~GPA+Sex,data=MedGPA)

GroupTable2=emplogitplot2(Acceptance~MCAT+Sex,ngroups=5,out=TRUE,data=MedGPA,putlegend="topleft")

emplogitplot2(Acceptance~MCAT+Sex,data=MedGPA,breaks=c(0,34.5,39.5,50.5),
              levelcol=c("red","blue"),putlegend="bottomright")

Description

Experiment on the effects of oxygen on sugar metabolism by bacteria

Format

A data frame with 16 observations on the following 3 variables.

Details

Many biochemical reactions are slowed or prevented by the presence of oxygen. For example, there are two simple forms of fermentation, one which converts each molecule of sugar to two molecules of lactic acid, and a second which converts each molecule of sugar to one each of lactic acid, ethanol, and carbon dioxide. This experiment was designed to compare the inhibiting effect of oxygen on the metabolism of two different sugars, glucose and galactose, by Streptococcus bacteria. In this case there were four levels of oxygen that were applied to the two kinds of sugar.

Renamed to SugarEthanol in second edition.

Source

Data are found in Statistics: The Exploration and Analysis of Data by Jay Devore and Roxy Peck (2008). St. Paul, MN: West.

The original article is Yamada T., Takahashi-Abbe S., Abbe K. (1985) "Effects of oxygen concentration on pyruvate formatelyase in situ and sugar metabolism of Streptocucoccus mutans and Streptococcus samguis," Infection and Immunity, pp. 129-134.

Description

Data from an experiment relating pupil dilation to sexual orientation.

Format

A data frame with 106 observations on the following 4 variables.

DilateDiff

Difference in pupil dilation when looking at same-sex and opposite-sex nude photographs

Sex

F=female or M=male

Gay

1=gay or 0=not, based on Kinsey scale score greater than 3

SexMale

0=female or 1=male

Details

DilateDiff is, essentially, the difference in pupil dilation when looking at (a) same-sex nudes and (b) opposite-sex nude photographs. More specifically, multiple measurements of pupil size were taken under each of the two conditions, together with a third condition that involved a neutral stimulus. Within-subject z-scores were then computed, which led to the DilateDiff numbers used here.

Source

G. Rieger and R.C. Savin-Williams (2012),"The Eyes Have It: Sex and Sexual Orientation Differences in Pupil Dilation Patterns," in PLoS ONE. The full study included 325 students. Here we are analyzing a subset of the data that excludes White students.

Description

Grip strength, attractiveness, and shoulder-hip ratio for men

Format

A data frame with 38 observations on the following 5 variables.

MaxGripStrength

Measurement of strength of hand grip

SHR

Shoulder to hip ratio

Partners

Number of sexual partners (lifetime)

Attractive

Attractiveness rating

AgeFirstSex

Age of first sex

Details

Facial attractiveness of several men was rated by female college students. Maximum grip strength was also measured, along with shoulder to hip ratio, age of first sex, and number of sex partners.

Source

Shoup, M. L. and Gallup, G.G., Jr. (2008), "Men's Faces Convey Information about Their Bodies and Their Behavior: What You See is What You Get," Evolutionary Psychology, 6(3): 469-479.

Description

Ratings from a facial photo and actual faithfulness.

Format

A data frame with 170 observations on the following 7 variables.

SexDimorph

Rating of sexual dimorphism (masculinity for males, femininity for females)

Attract

Rating of attractiveness

Cheater

Was the face subject unfaithful to a partner? (1=yes or 0=no)

Trust

Rating of trustworthiness

Faithful

Rating of faithfulness

FaceSex

Sex of face (F=female or M=male)

RaterSex

Sex of rater (F=female or M=male)

Details

College students were asked to look at a photograph of an opposite-sex adult face and to rate the person, on a scale from 1 (low) to 10 (high), for attractiveness. They were also asked to rate trustworthiness, faithfulness, and sexual dimorphism (i.e., how masculine a male face is and how feminine a female face is). Overall, 68 students (34 males and 34 females) rated 170 faces (88 men and 82 women).

Source

This dataset is based on G. Rhodes et al. (2012), "Women can judge sexual unfaithfulness from unfamiliar men's faces," Biology Letters, November 2012. All of the 68 raters were heterosexual Caucasians, as were the 170 persons who were rated. (We have deleted 3 subjects with missing values and 16 subjects who were over age 35.)

Description

Draft selection times for a fantasy baseball league

Format

A data frame with 24 observations on the following 9 variables.

Details

Time (in seconds) for participants in a draft for a fantasy baseball league to make a selection at each round.

Source

Mathematical Science Baseball League historical records (online).

Description

Experiment on effects of diets on weight gain of rats

Format

A data frame with 60 observations on the following 3 variables.

Gain

Weight gain (in grams per week)

Protein

Level of protein (Hi or Lo)

Source

Source of protein (Beef, Cereal, or Pork)

Details

Data from this experiment compared weight gain for 60 baby rats that were fed different diets. Half of the rats had low-protein diets (Lo) and the rest had high-protein (Hi). The source of protein was either beef, cereal, or pork.

Source

C. P. Wilsie, Iowa State College Agricultural Station (1944) via Snedecor and Cochran

Description

Fertility measurements for a sample of women who have difficulty getting pregnant

Format

A data frame with 333 observations on the following 10 variables.

Details

A medical doctor and her team of researchers collected a variety of data on women who were having trouble getting pregnant. A key method for assessing fertility is a count of antral follicles (LowAFC or MeanAFC) that can be performed with noninvasive ultrasound. Researchers are interested in how the other variables are related to these counts.

Source

We thank Dr. Priya Maseelall and her research team for sharing these data.

Description

Field goal results in the National Football League (NFL) by distance

Format

A data frame with 51 observations on the following 7 variables.

Details

This dataset summarizes all 8520 field goals attempted by place kickers in the National Football League (NFL) during regular season games for the 2000 through the 2008 seasons. Results are counts (attempted, made, and blocked) and proportions (made and blocked) for each distance.

Source

We thank Sean Forman and Doug Drinen of Sports Reference LLC for providing us with the NFL field goal data set.

Description

Film data from Maltin's Movie and Video Guide

Format

A data frame with 100 observations on the following 9 variables.

Details

One statistician movie fan decided to use statistics to study the movie ratings in his favorite movie guide, Movie and Video Guide (1996), by Leonard Maltin. Maltin rates movies on a one-star to four-star system, in increments of half-stars, with higher numbers being better. The guide also includes additional information on each film. The statistician used a random number generator to select a simple random sample of 100 movies rated by the Guide.

Source

Data from Leonard Maltin's Movie and Video Guide (1996)

Description

NCAA Final Four by seed with indicator for Tom Izzo's teams from 1985 - 2010.

Format

A dataset with 1664 observations on the following 4 variables.

Details

Each year 64 college teams are selected for the NCAA Division I Men's Basketball tournament, with 16 teams placed in each of four regions. Within each region the teams are seeded from 1 to 16, with the (presumed) best team as the 1 seed and the (presumed) weakest team as the 16 seed; this practice of seeding teams began in 1979 for the NCAA tournament. Only one team from each region (so four teams each year) advances to the Final Four. This dataset is the same as FinalFourLong, except the data starts in 1985 and we have a extra column that is an indicator for Michigan State teams coached by Tom Izzo.

Updated to FinalFourIzzo17 in second edition.

Source

Final Four teams and their seed can be found at
http://www.championshiphistory.com/ncaahoops.php.

Description

NCAA Final Four by seed with indicator for Tom Izzo's teams for 1985 - 2017

Format

A data frame with 2112 observations on the following 4 variables.

Year

Year 1985 - 2017

Seed

Seed in NCAA men's basketball tournament: 1 to 16

Final4

1=made Final Four or 0=did not make Final Four

Izzo

1=team coached by Tom Izzo or 0=not an Izzo team

Details

Each year 64 college teams are selected for the NCAA Division I Men's Basketball tournament, with 16 teams placed in each of four regions. Within each region the teams are seeded from 1 to 16, with the (presumed) best team as the 1 seed and the (presumed) weakest team as the 16 seed; this practice of seeding teams began in 1979 for the NCAA tournament. Only one team from each region (so four teams each year) advances to the Final Four. This dataset is an extention of FinalFourIzzo (that ended in 2017) and the same as FinalFourLong2017, except the data starts in 1985 and we have an extra column that is an indicator for Michigan State teams coached by Tom Izzo.

Source

Final Four teams and their seed can be found at http://www.championshiphistory.com/ncaahoops.php

Description

NCAA Final Four by seed with individual cases for each team each year

Format

A data frame with 2048 observations on the following 3 variables.

Details

Each year 64 college teams are selected for the NCAA Division I Men's Basketball tournament, with 16 teams placed in each of four regions. Within each region the teams are seeded from 1 to 16, with the (presumed) best team as the 1 seed and the (presumed) weakest team as the 16 seed; this practice of seeding teams began in 1979 for the NCAA tournament. Only one team from each region (so four teams each year) advances to the Final Four. This dataset has a row (case) for each team in the NCAA Division I Men's Basketball tournament from 1979 to 2010 along with its seed and an indicator for whether the team made the Final Four that year.

Updated to FinalFourLong17 in second edition.

Source

Final Four teams and their seed can be found at
http://www.championshiphistory.com/ncaahoops.php.

Description

NCAA Final Four by seed with individual cases for each team each year

Format

A data frame with 2496 observations on the following 4 variables.

Year

Year (1979 - 2017)

Seed

Seed in NCAA men's basketball tournament: 1 to 16

Final4

1=made Final Four or 0=did not make Final Four

Details

Each year 64 college teams are selected for the NCAA Division I Men's Basketball tournament, with 16 teams placed in each of four regions. Within each region the teams are seeded from 1 to 16, with the (presumed) best team as the 1 seed and the (presumed) weakest team as the 16 seed; this practice of seeding teams began in 1979 for the NCAA tournament. Only one team from each region (so four teams each year) advances to the Final Four. This dataset has a row (case) for each team in the NCAA Division I Men's Basketball tournament from 1979 to 2017 along with its seed and an indicator for whether the team made the Final Four that year. This dataset is an extention of FinalFourLong (that went through 2010).

Source

Final Four teams and their seed can be found at
http://www.championshiphistory.com/ncaahoops.php

Description

NCAA Final Four participation summarized each year by seed

Format

A data frame with 512 observations on the following 4 variables.

Details

Each year 64 college teams are selected for the NCAA Division I Men's Basketball tournament, with 16 teams placed in each of four regions. Within each region the teams are seeded from 1 to 16, with the (presumed) best team as the 1 seed and the (presumed) weakest team as the 16 seed; this practice of seeding teams began in 1979 for the NCAA tournament. Only one team from each region (so four teams each year) advances to the Final Four. This dataset is similar to FinalFourLong, except that each row combines the count of the results (make/don't make the Final Four) for each seed, so that In+Out= 4 for each row.

Updated to FinalFourShort17 in second edition.

Source

Final Four teams and their seed can be found at
http://www.championshiphistory.com/ncaahoops.php.

Description

NCAA Final Four participation summarized each year by seed

Format

A data frame with 624 observations on the following 4 variables.

Year

Year 1979 to 2017

Seed

Seed in NCAA men's basketball tournament: 1 to 16

In

Number of teams at that seed who made the Final Four that year

Out

Number of teams at that seed who did not made the Final Four that year

Details

Each year 64 college teams are selected for the NCAA Division I Men's Basketball tournament, with 16 teams placed in each of four regions. Within each region the teams are seeded from 1 to 16, with the (presumed) best team as the 1 seed and the (presumed) weakest team as the 16 seed; this practice of seeding teams began in 1979 for the NCAA tournament. Only one team from each region (so four teams each year) advances to the Final Four. This dataset is similar to FinalFourLong2017, except that each row combines the count of the results (make/don't make the Final Four) for each seed, so that In+Out= 4 for each row. This dataset is an extention of FinalFourShort (that went though 2010).

Source

Final Four teams and their seed can be found at
http://www.championshiphistory.com/ncaahoops.php

Description

Finger tap rates after drug administration

Format

A data frame with 12 observations on the following 4 variables.

Subject

Subject code (I, II, III, or IV)

Drug

Drug administered (Ca=caffeine, Pl=placebo, or Th=theobromine)

TapRate

Finger taps in a fixed time interval

Details

Scientists Scott and Chen, published research that compared the effects of caffeine with those of theobromine (a similar chemical found in chocolate) and with those of a placebo. Their experiment used four human subjects, and took place over several days. Each day each subject swallowed a tablet containing one of caffeine, theobromine, or the placebo. Two hours later they were timed while tapping a finger in a specified manner (that they had practiced earlier, to control for learning effects). The response is the number of taps in a fixed time interval.

Renamed FranticFingers in second edition.

Source

The data was found in Statistics in Biology, Vol. 1, by C. I. Bliss (1967), New York: McGraw Hill.

The original article is Scott, C. and Chen, K. (1944) "Comparison of the action of 1-ethyl theobromine and caffeine in animals and man," Journal of Pharmacological Experimental Therapy, v. 82, pp 89-97.

Description

Predicting first-year college GPA

Format

A data frame with 219 observations on the following 10 variables.

Details

The data in FirstYearGPA contains information from a sample of 219 first year students at a midwestern college that might be used to build a model to predict their first year GPA.

Source

A sample from a larger set of data collected in 1996 by a professor at this college.

Description

Fertility measurement for eggs from a sample of 35 lake trout

Format

A data frame with 35 observations on the following 4 variables.

Details

Researchers collected samples of female lake trout from Lake Ontario in September and November of 2002 through 2004. A goal of the study was to investigate the fertility of fish that had been stocked in the lake. One measure of the viability of fish eggs is percent dry mass (PctDM) which reflects the energy potential stored in the eggs by recording the percentage of the total egg material that is solid. Values of the PctDM for a sample of 35 lake trout (14 in September and 21 in November) are given in this dataset along with the age (in years) of the fish.

Source

Lantry, OGorman, and Machut (2008) "Maternal Characteristics versus Egg Size and Energy Density," Journal of Great Lakes Research 34(4): 661-674.

Description

Body measurements for a sample of 28 mammal species from a Fitch paper on acoustic allometry

Format

A data frame with 28 observations on the following 5 variables.

Species

species of mammal

Order

Order (Carnivora or Primates)

Wt

Body weight (in kg)

Skull

Skull length (in cm)

Palate

Palate length (in cm)

Details

Data on mammal species from a Zoology paper about acoustic allometry by W. Tecumseh Fitch.

Source

Fitch, W. Tecumseh (2000), "Skull dimensions in relation to body size in nonhuman mammals: The causal bases for acoustic allometry," Zoology, 103, 40-58.

Description

Flight response of Pacific Brant to overflights of helicopters

Format

A dataset with 464 observations on the following 7 variables.

Details

A 1994 study collected data on the effects of air traffic on the behavior of the Pacific Brant (a small migratory goose). The data represent the flight response to helicopter "overflights" to see what the relationship between the proximity of a flight, both lateral and altitudinal, would be to the propensity of the Brant to flee the area. For this experiment, air traffic was restricted to helicopters because previous study had ascertained that helicopters created more radical flight response than other aircraft. The data are in FlightResponse. Each case represents a flock of Brant that has been observed during one overflight in the study. Flocks were determined observationally as contiguous collections of Brants, flock sizes varying from 10 to 30,000 birds.

Source

Data come from the book Statistical Case Studies: A Collaboration Between Academe and Industry, Roxy Peck, Larry D. Haugh, and Arnold Goodman, editors; SIAM and ASA, 1998.

Description

Florida death penalty cases by race of defendant and victim

Format

A data frame with 326 observations on the following 4 variables.

Penalty

Was death penalty given? (No or Yes)

Defendant

Race of the defendant (Black or White)

White.Victim

Was the victim white? (1=yes or 0=no)

Black.Victim

Was the victim black? (1=yes or 0=no)

Details

Mike Radelet's data on imposition of the death penalty for murderers in Florida broken down by race of the victim and defendant.

Source

Radelet, M. (1981), "Racial Characteristics and Imposition of the Death Penalty," American Sociological Review, 46, 918-927.

Description

Data from an experiment on calcium binding to proteins

Format

A data frame with 51 observations on the following 2 variables.

Details

Suzanne Rohrback used a novel approach in a series of experiments to examine calcium binding proteins.

Source

Thanks to Suzanne Rohrback for providing these data from her honors experiments at Kenyon College.

Description

Finger tap rates after drug administration

Format

A data frame with 12 observations on the following 4 variables.

ID

Case ID

Rate

Finger taps in a fixed time interval

Subj

Subject code (A, B, C, or D)

Drug

Drug administered (Ca=caffeine, Pl=placebo, or Th=theobromine)

Details

Scientists Scott and Chen published research that compared the effects of caffeine with those of theobromine (a similar chemical found in chocolate) and with those of a placebo. Their experiment used four human subjects and took place over several days. Each day each subject swallowed a tablet containing one of caffeine, theobromine, or the placebo. Two hours later they were timed while tapping a finger in a specified manner (that they had practiced earlier, to control for learning effects). The response is the number of taps in a fixed time interval.

Source

The data was found in Statistics in Biology, Vol. 1, by C. I. Bliss (1967), New York: McGraw Hill.

The original article is Scott, C.C. and Chen, K. K. (1944), "Comparison of the action of 1-ethyl theobromine and caffeine in animals and man," Journal of Pharmacological Experimental Therapy, v. 82, pp 89-97.

Description

Sexual activity and lifetimes of fruit flies

Format

A data frame with 125 observations on the following 7 variables.

Details

Hanley and Shapiro (1994) report on a study conducted by Partridge and Farquhar (1981) about the sexual behavior of fruit flies. It was already known that increased reproduction leads to shorter life spans for female fruit flies. But the question remained whether an increase in sexual activity would also reduce the life spans of male fruit flies. The researchers designed an experiment to answer this question. They had a total of 125 male fruit flies to use and they randomly assigned each of the 125 to one of the following five groups.

Source

The data are given as part of the data archive on the Journal of Statistics Education website and can be found on the page
http://www.amstat.org/publications/jse/jse_data_archive.htm.

References

Hanley and Shapiro, (1994) "Sexual Activity and the Lifespan of Male Fruitflies: A Dataset That Gets Attention," Journal of Statistics Education v.2, n.1
http://www.amstat.org/publications/jse/v2n1/datasets.hanley.html

Description

Results from an experiment on male fruit flies with different levels of sexual activity and competition from other males

Format

A data frame with 201 observations on the following 7 variables.

Mated

Was the fly allowed mating opportunities? (n or y)

Alone

Did the fly live alone? (y=yes or n= no, lived near another male)

Mating

How many mating opportunities was the fly given?

Total

Total duration of mating time over all opportunities (in seconds)

Size

Size of the thorax (in mm)

Lifespan

Lifespan (in hours, starting at the 12th day)

Activity

Number of times a movement detector was tripped starting in the 12th day

Details

Researchers randomly assigned virgin male fruit flies to one of two treatments: live alone or live in an environment where they can sense one other male fly. Flies were randomly allocated to either have mating opportunities with female flies or to not have such opportunities. Those flies that were given mating opportunities were given 3, 4, or 5 opportunities to mate (Mating measures this number). Researchers also measured size, lifespan and activity levels of the fruit flies.

Source

The file we are using is the link called survival at
http://rsbl.royalsocietypublishing.org/content/suppl/2013/02/25/rsbl.2012.1188.DC1.html

The article talking about the data is at
http://rsbl.royalsocietypublishing.org/content/9/2/20121188.full

Description

Experiment with a ball swirling thorough a funnel

Format

A data frame with 120 observations on the following 3 variables.

Funnel

Height of the funnel (inches)

Tube

Height of the drop tube (inches)

Time

Time (in seconds) for the ball to drop/swirl though the funnel

Details

Data from a class experiment to see where a steel ball was rolled through a plastic tube into a long plastic funnel. The angle of the funnel and the angle of the tube with respect to the flat table could be adjusted by changing the height of either (Funnel measured from the table, Tube measured from the top of the funnel). The ball rolls down the tube, then swirls around the funnel until dropping out at the bottom. Total trip time was measured with a stopwatch. Heights were adjusted after every two drops in a randomized order.

Source

The funnel dropping experiment was originally described in Gunter, B. (1993) "Through a Funnel Slowly with Ball Bearing and Insight to Teach Experimental Design," The American Statistician, Vol. 47. These data come from a class experiment based on the setup in that article.

Description

Brightness and fecundity of female glow-worms

Format

A data frame with 26 observations on the following 2 variables.

Lantern

Length of glow lantern (in mm)

Eggs

Number of eggs laid

Details

Data on 26 female glow-worms captured in Finland. Female glow-worms attract males by glowing with part of their abdomen (lantern). Researchers believe the brightness of glow might be related to mating success.

Source

Hopkins J, Baudry G, Candolin U, Kaitala A. (2015), "I'm sexy and I glow it: female ornamentation in a nocturnal capital breeder," Biol. Lett. 11: 20150599.
http://dx.doi.org/10.1098/rsbl.2015.0599

Description

Measurements for a sample of goldenrod galls

Format

A data frame with 1055 observations on the following 9 variables.

Details

Biology students collected measurements on goldenrod galls at the Brown Family Environmental Center at Kenyon College.

Source

Thanks to the Kenyon College Department of Biology for sharing these data.

Description

Data on houses sold between 2005 and 2015 in Grinnell, Iowa

Format

A data frame with 929 observations on the following 15 variables.

Date

Coded value for date of sale (Jan 1, 2005=16436)

Address

Street address of the house

Bedrooms

Number of bedrooms

Baths

Number of bathrooms

SquareFeet

The square footage of the home's living space

LotSize

Lot size (in acres)

YearBuilt

Year the house was built; many pre-1900 homes are listed as 1900

YearSold

The year the house was sold, for this case

MonthSold

The month the house was sold (1=Jan, 2=Feb, to 12=Dec)

DaySold

Day of the month the house was sold (1 to 31)

CostPerSqFt

SalePrice / SquareFeet (round to nearest penny)

OrigPrice

List price of the house when originally put on the market (dollars)

ListPrice

List price at the time of sale (dollars)

SalePrice

Sale price of the house (dollars)

SPLPPct

(Sale_Price / List_Price ) * 100

Details

A local Grinnell realtor, Matt Karjalahti, put these data together to see what patterns might be found, perhaps with an improvement in how one sells houses or buys them. He asked Grinnell College economists, Lee Logan and Eric Ohrn, to help with the analysis and we obtained the data from them.

Source

Thanks to Grinnell realtor Matt Karjalahti who originally collected the data and Grinnell College economists Lee Logan and Eric Ohrn who gave us the data.

Description

Grocery store sales with different discounts

Format

A data frame with 36 observations on the following 5 variables.

Details

Grocery stores and product manufacturers are always interested in how well the products on the store shelves sell. An experiment was designed to test whether the amount of discount given on products affected the amount of sales of that product. There were three levels of discount, 5%, 10%, and 15%, and sales were held for a week. The total number of products sold during the week of the sale was recorded. The researchers also recorded the wholesale price of the item put on sale.

Source

These data are not real, though they are simulated to approximate an actual study. The data come from John Grego, Director of the Stat Lab at University of South Carolina.

Description

Presence/absence of gunnels (eels) at shoreline quadrats

Format

A data frame with 1592 observations on the following 10 variables.

Details

This dataset comes from a study on the habitat preferences of a species of eel, called a gunnel. Biologist Jake Shorty sampled quadrats along a coastline and recorded whether or not the species was found in the quadrat.

Source

Thanks to Jake Shorty, Bowdoin biology student, for this dataset.

Description

Survey data to see if subjects can guess author's sex from handwriting specimens

Format

A data frame with 204 observations on the following 8 variables.

Individual

Survey Respondent Number

Gender

Gender of Respondent (0 = male, 1 = female)

Survey1

Percent correct on Survey 1

Survey2

Percent correct on Survey 2

FemaleID

Percent correct in identifying female specimens on Survey 1

MaleID

Percent correct in identifying male specimens on Survey 1

Both

Percent correctly identified on Survey 1 AND Survey 2

DIFF

Survey1 - Survey2

Details

Bradley and colleagues at Clarke University gave two identical surveys to a sample of 203 students (each student did the survey twice). Each survey contains 25 writing specimens and students were asked to identify whether the author is male or female. Of the 25 specimens, 12 are written by a female, 13 by a male.

An example of the survey form can be found at
https://docs.google.com/forms/d/1sO6vlsozsORbqaCTsA7Ta0qZL7_6_MCEPJ7tYeKYyvI/viewform

Source

Bradley, S., (2015), "Handwriting and Gender: A Multi-use Dataset", JSE (Datasets and Stories). March 2015.

http://www.amstat.org/publications/jse/v23n1/bradley.pdf

Description

Data for a samples of hawks from three different species

Format

A data frame with 908 observations on the following 19 variables.

Details

Students and faculty at Cornell College in Mount Vernon, Iowa, collected data over many years at the hawk blind at Lake MacBride near Iowa City, Iowa. The data set that we are analyzing here is a subset of the original data set, using only those species for which there were more than 10 observations. Data were collected on random samples of three different species of hawks: Red-tailed, Sharp-shinned, and Cooper's hawks.

Source

Many thanks to the late Professor Bob Black at Cornell College for sharing these data with us.

Description

Tail lengths for two hawk species

Format

A data frame with 838 observations on the following 2 variables.

Details

Tail lengths measured for a sample of 838 hawks observed in Mount Vernon, Iowa. Note: HawkTail2 has these data in unstacked format and they are a subset of the data in Hawks which has a third species (Cooper's hawk).

Source

Observations by students and faculty at Cornell College.

Description

Tail lengths for two hawk species

Format

A data frame with observations on the following 2 variables.

Details

Tail lengths measured for a sample of hawks observed in Mount Vernon, Iowa. Note: HawkTail has similar data in stacked format. The Hawks dataset has more variables and a third species (Cooper's hawk).

Source

Observations by students and faculty at Cornell College.

Description

Percentaged of correctly identified words in a hearing test

Format

A data frame with 96 observations on the following 3 variables.

Details

Audiologists use standard lists of 50 words to test hearing; the words are calibrated, using subjects with normal hearing, to make all 50 words on the list equally hard to hear. The goal of the study described here was to see how four such lists, denoted by L1-L4 in this dataset, compared when played at low volume with a noisy background. The response is the percentage of words identified correctly.

Source

Data downloaded from DASL at http://lib.stat.cmu.edu/DASL/Datafiles/Hearing.html.

References

Loven, F. (1981), "A Study of the Interlist Equivalency of the CID W-22 Word List Presented in Quiet and in Noise." Unpublished MS Thesis, University of Iowa.

Description

Monthly US residential consumption of fuel oil (1983-2016)

Format

A data frame with 408 observations on the following 4 variables.

Year

Year (1983 to 2016)

Month

Month (1=Jan through 12=Dec)

t

Time index (1 to 408)

FuelOil

Residential consumption of fuel oil (in 1,000 barrels/day)

Details

U.S. residential consumption of distillate fuel oil each month from January 1983 through December 2016.

Source

U.S. Energy Information Administration website, https://www.eia.gov/totalenergy/data/monthly/index.php

Description

Data on hiking trails for each of the 46 "High Peaks" in the Adirondack mountains

Format

A data frame with 46 observations on the following 6 variables.

Details

Forty-six mountains in the Adirondacks of upstate New York are known as the High Peaks with elevations near or above 4000 feet (although modern measurements show a couple of the peaks are actually slightly under 4000 feet). A goal for hikers in the region is to become a "46er" by scaling each of these peaks. This dataset gives information about the hiking trails up each of these peaks.

Source

High Peaks data avaialble at http://www.adirondack.net/tour/hike/highpeaks.cfm. Thanks to Jessica Chapman at St. Lawrence University for recommending this dataset.

Description

Data from games played by the Grinnell College men's basketball team between 1997 and 2006

Format

A data frame with 147 observations on the following 22 variables.

Details

Since 1991, David Arseneault, men's basketball coach of Grinnell College, has developed a unique, fast-paced style of basketball that he calls "the system." This dataset comes from the 147 games the Grinnell team played within its athletics conference between the 1997-98 season through the 2005-06 season.

Source

These data were collected by Grinnell College students Eric Ohrn and Ben Johannsen.

Description

Price and related characteristics of horses listed for sale on the internet

Format

A data frame with 50 observations on the following 5 variables.

Details

Undergraduate students at Cal Poly collected data on prices of 50 horses advertised for sale on the internet. Predictor variables of price include the age and height of the horse (in hands), as well as its sex.

Source

Cal Poly students using a horse sale website.

Description

Selling price and characteristics for a sample of 20 houses in a small town

Format

A data frame with 20 observations on the following 3 variables.

Details

This dataset contains selling prices for 20 houses that were sold in 2008 in a small midwestern town. The file also contains data on the size of each house (in square feet) and the size of the lot (in square feet) that the house is on.

Updated to HousesNY in second edition.

Source

Data collected from zillow.com in June 2008.

Description

House prices for a sample of houses in Canton NY

Format

A data frame with 53 observations on the following 5 variables.

Price

Estimated price (in $1,000's)

Beds

Number of bedrooms

Baths

Number of bathrooms

Size

Floor area of the house (in 1,000 square feet)

Lot

Size of the lot (in acres)

Details

Data scraped from Zillow.com for a sample of houses near the 13617 area code (Canton, NY a small town in upstate NY). Houses on lots bigger than five acres (often farms) were excluded.

Source

Data scraped from the Zillow.com website using tools an app at http://myslu.stlawu.edu/~clee/dataset/zillow/ (April 2017)

Description

Data for a sample of 200 patients at an Intensive Care Unit (ICU)

Format

A data frame with 200 observations on the following 9 variables.

Details

This dataset contains information for a sample of 200 patients who were part of a larger study conducted in a hospital's Intensive Care Unit (ICU). Since an ICU often deals with serious, life-threatening cases, a key variable to study is patient survival, which is coded in the Survive variable as 1 if the patient lived to be discharged and 0 if the patient died.

Source

Data downloaded from The Data and Story Library (DASL), http://lib.stat.cmu.edu/DASL/Datafiles/ICU.html.

Description

Infant mortality rates in the United States by decade (1920-2010)

Format

A data frame with 10 observations on the following 2 variables.

Mortality

Deaths within one year of birth (per 1000 births)

Year

Year (1920-2010 by decades)

Details

Infant mortality (deaths within one year of birth per 1,000 births) in the US from 1920 - 2010 (by decade).

Source

CDC National Vital Statistics Reports at http://www.cdc.gov/nchs/data/nvsr/nvsr57/nvsr57_14.pdf and https://www.cdc.gov/nchs/data/nvsr/nvsr64/nvsr64_09.pdf

Description

Consumer Price Index (CPI) each month for 2009 through 2016

Format

A data frame with 96 observations on the following 5 variables.

Month

Month: 1=January to 12=December

Year

Year (2009 to 2016)

CPI

Consumer Price Index (base=100 in 1984)

CPIPctDiff

Monthly percent change in CPI

t

Time index (1 to 96)

Details

Monthly Consumer Price Index for 2009 to 2016 as produced by the Bureau of Labor Statistics (Series Id. CUUR0000SA0). Based on prices for all items in U.S. city average for all consumers (not seasonally) Base period is 1982-1984-100.

Source

Data downloaded from Bureau of Labor Statistics at
https://www.bls.gov/data/

Description

Congressional votes on an ObamaCare health insurance bill in 2009

Format

A dataset with 435 observations on the following 9 variables.

Details

On 7 November 2009 the U.S. House of Representatives voted, by the narrow margin of 220-215, for a bill to enact health insurance reform. Most Democrats voted yes while almost all Republicans voted no. This dataset contains data for each of the 435 representatives.

Source

Insurance data are from the American Community Survey
(http://www.census.gov/acs/www/data_documentation/data_main/). Roll call of congressional votes on this bill can be found at
http://clerk.house.gov/evs/2009/roll887.xml.

Description

True IQ and guessed IQ (from a photo) for 40 women

Format

A data frame with 40 observations on the following 3 variables.

Age

Age of woman

GuessIQ

Guessed IQ

TrueIQ

Actual IQ

Details

One hundred sixty raters (75 men and 85 women) took part in judging intelligence (on a 1=high to 7=low scale) based on photographs of students. The ratings were converted to z-scores and then put on an IQ scale to compare to actual measured IQ. There were photos of 80 students, 40 men and 40 women. This data set contains data for the 40 women.

Source

Kleisner K, Chvatalova V, Flegr J (2014), "Perceived Intelligence Is Associated with Measured Intelligence in Men but Not Women," PLoS ONE 9(3): e81237. doi:10.1371/journal.pone.0081237.

Description

Reporting rates for bi-weekly jury pools in Franklin County Court (Columbus, OH).

Format

A data frame with 52 observations on the following 4 variables.

Details

Tom Shields, jury commissioner for the Franklin County Municipal Court in Columbus, Ohio, is responsible for making sure that the judges have enough potential jurors to conduct jury trials. Jury duty for this court is two weeks long, so Tom must bring together a new group of potential jurors twenty-six times a year. Random sampling methods are used to obtain a sample of registered voters in Franklin County every two weeks, and these individuals are sent a summons to appear for jury duty. One of the most difficult aspects of Tom's job is to get those registered voters who receive a summons to actually appear at the courthouse for jury duty. This dataset contains the 1998 and 2000 data for the percentages of individuals who reported for jury duty after receiving a summons. The reporting dates vary slightly from year to year, so they are coded sequentially from 1, the first group to report in January, to 26, the last group to report in December. A variety of methods were used after 1998 to try to increase participation rates.

Source

Franklin County Municipal Court

Description

Pitch-by-pitch data for baseball pitcher Clayton Kershaw in the 2013 season

Format

A data frame with 3402 observations on the following 24 variables.

BatterNumber

Number of batters faced so far that game

Outcome

One of 14 possible results for a pitch (e.g. Ball, Ball In Dirt, Called Strike, ..., Swinging Strike (Blocked))

Class

One of three classifications (B=ball, S=strike, or X=in play)

Result

From pitcher's perspective (Neg=ball or hit, Pos=strike or out)

Swing

Did the batter swing at the pitch? (No or Yes)

Time

Date and time of the pitch (format yyyy-mm-ddThh:mm:ssZ)

StartSpeed

Speed leaving the pitcher's hand (in mph)

EndSpeed

Speed crossing home plate (in mph)

HDev

Horizontal movement (inches)

VDev

Vertical movement (inches)

HPos

Horizontal position at home plate (inches from center, positive is catcher's right)

VPos

Vertical position at home plate (inches above the ground)

PitchType

Code for pitch type (CH=changeup, CU=curve, FF=fastball, or SL=slider)

Zone

1-9 in theoretical strike zone (upper left to lower right), 11-14 are out of strike zone

Nasty

A measure on a 0-100 scale of difficulty of the pitch to hit (100 is most difficult)

Count

Ball strike count (0-0, 0-1, 0-2, 1-1, 1-2, 2-1, 2-2, 3-1, or 3-2)

BallCount

Number of balls before the pitch (0, 1, 2, or 3)

StrikeCount

Number of strikes before the pitch (0, 1, or 2)

Inning

Inning of the game

InningSide

Portion of the inning (bottom= pitcher at home or top=pitcher away)

Outs

Number of outs when the pitch is thrown

BatterHand

Batter's stance (L=left or R=right)

ABEvent

Result of the at bat (several possibilities)

Batter

Name of the batter faced

Details

Dataset includes information for 3,402 individual pitches thrown by Los Angeles Dodger baseball pitcher Clayton Kershaw during the 2013 regular season when he won the Cy Young award as the best pitcher in the National League. Many variables are measured using Major League Baseball's PITCHf/x system that uses camera systems in each ballpark to track characteristics of each pitch thrown.

Source

Data scraped from the MLB GameDay website (http://gd2.mlb.com/components/game/mlb/) using pitchRx

Description

Hourly water temperatures from Gulf of Mexico near Key West, Florida

Format

A data frame with 6572 observations on the following 3 variables.

DateTime

Date and time of reading (format mm/dd/yyyy h:00)

WaterTemp

Water temperature (in degrees Fahrenheit)

t

Time index (1 to 673)

Details

Hourly readings of water temperatures from a measuring device in the Gulf of Mexico near Key West, Florida. The hourly temperatures are provided from October 3, 2016 to October 3, 2017 and were obtained from station 8724580. A few missing values have been interpolated to provide a complete series.

Source

National Oceanographic and Atmospheric Administration (2017), Key West Ocean Temperature Data, October 3, 2016 to October 3, 2017, https://www.nodc.noaa.gov, Accessed on October 4, 2017

Data were obtained by Kyle Johnston for his Senior Exercise (a capstone project).

Description

Body measurements for a sample of 198 children

Format

A data frame with 198 observations on the following 5 variables.

Details

This dataset comes from a 1977 anthropometric study of body measurements for children. Subjects in this sample are between the ages of 8 and 18 years old, selected at random from the much larger dataset of the original study.

Source

A sample of 198 cases from the NIST's AnthroKids dataset at http://ovrt.nist.gov/projects/anthrokids/

Description

Lifetimes for potato leafhoppers on various sugar diets

Format

A data frame with 8 observations on the following 2 variables.

Details

The goal of this study was to compare the effects of four diets on the lifespan of small insects called potato leafhoppers. One of the four was a control diet: just distilled water with no nutritive value. Each of the other three diets had a particular sugar added to the distilled water, one of glucose, sucrose, or fructose. Leafhoppers were sorted into groups of eight and each group was put into one of eight lab dishes. Each of the four diets was added to two dishes, chosen using chance.

Source

"Survival and behavioral responses of the potato leafhopper, Empoasca Fabae (Harris), on synthetic media," MS thesis by Douglas Dahlman (1963), Iowa State University. The data can be found in Analyzing Experimental Data by Regression by David M. Allen and Foster B. Cady, Belmont, CA: Lifetime Learning (Wadsworth).

Description

Measurements of Dodonaea viscosa leaves

Format

A data frame with 252 observations on the following 5 variables.

Width

Average width (in mm)

Length

Average length (in mm)

LWRatio

Length divided by Width

Area

Area (in sq. mm)

Year

Year the leaves were collected

Details

Data on samples of leaves from the species Dodonaea viscosa subsp. angustissima (common name hopbush), which have been collected in a certain region of South Australia for many years.

Source

Guerin, G., Wen, H., Lowe, A. (2012), "Leaf morphology shift linked to climate change," Biol. Lett., 8, doi: 10.1098/rsbl.2012.0458

Description

Treatment results for leukemia patients

Format

A data frame with 51 observations on the following 9 variables.

Details

A study involved 51 untreated adult patients with acute myeloblastic leukemia who were given a course of treatment, after which they were assessed as to their response.

Source

Data come from Statistical Analysis Using S-Plus (Brian S. Everitt; first edition 1994, Chapman & Hall).

Description

Factors relating to Mississippi River levee failure

Format

A data frame with 82 observations on the following 14 variables.

Failure

Did the levee fail? (1=yes or 0=no)

Year

Year

RiverMile

Location along the river (mile marker)

Sediments

Sediments present? (1=yes or 0=no)

BorrowPit

Borrow pit present? (1=yes or 0=no)

Meander

Type of meander (1=inside bend, 2=outside bend, 3=chute, 4=straight)

ChannelWidth

Width of the river channel (in meters)

FloodwayWidth

Width of floodway (in meters, levee to levee, levee to bluff, or bluff to bluff, as appropriate)

ConstrictionFactor

Constriction of the floodway over time (1880s to present)

LandCover

1=open water, 2=grassy, 3=agricultural, 4=forest

VegWidth

Vegative buffer width (in meters)

Sinuosity

River length divided by valley length for 10 miles up- and down-valley from levee site

Dredging

Dredging intensity

Revetement

Is there a stone structure (wall) meant to hold up the bank? (1=yes or 0=no)

Details

The goal of this investigation was to test the relative importance of geologic, geomorphic, and other physical factors that have led to levee failures through the past century along much of the Mississippi River.

Source

A. Flor, N. Pinter, W.F. Remo (2010), "Evaluating Levee Failure Susceptibility on the Mississippi River Using Logistic Regression Analysis," Engineering Geology, Vol. 116, pp. 139-148

Description

Dementia study comparing two groups of patients

Format

A data frame with 39 observations on the following 3 variables.

Type

DLB=Dementia with Lewy Bodies or DLB/AD=DLB and Alzheimer's Disease

APC

Annualized Percentage Change from baseline volume of the brain

MMSE

Change in functional performance on the Mini Mental State Examination

Details

Brain MRIs were used to study the brains of patients with Dementia with Lewy Bodies, some of whom also were diagnosed with Alzheimer's Disease.

Source

Z. Nedelksa et al. (2015), "Pattern of brain atrophy rates in autopsy-confirmed dementia with Lewy bodies,"" Neurobiology of Aging, 36: 452-461.

Description

Dementia Study with Lewy Bodies

Format

A data frame with 20 observations on the following 3 variables.

group

DLB/AD=DLB and Alzheimer's Disease

APC

Annualized Percentage Change from baseline volume of the brain

MMSE

Change in functional performance on the Mini Mental State Examination

Details

Brain MRIs were used to study the brains of patients with Dementia with Lewy Bodies. These are the cases that were also diagnosed with Alzheimer's Disease. This is a subset of LewBody2Groups

Source

Z. Nedelksa et al. (2015), "Pattern of brain atrophy rates in autopsy-confirmed dementia with Lewy bodies," Neurobiology of Aging, 36: 452-461.

Description

Winning distances in men's Olympic long jump competitions (1900 - 2008)

Format

A data frame with 26 observations on the following 2 variables.

Details

Gold medal winning distances for the men's long jump at the Olympics from 1900 to 2008.

Updated to LongJumpOlympics2016 in second edition.

Source

Historical Olympic long ump results at http://trackandfield.about.com/od/longjump/qt/olymlongjumpmen.htm

Description

Gold medal distance for Olympic men's long jump

Format

A data frame with 28 observations on the following 2 variables.

Year

Olympic Year (1900-2016)

Gold

Gold medal distance (in meters)

Details

Gold medal winning distances for the men's long jump at the Olympics from 1900 to 2016.

Source

Historical Olympic long jump results at http://trackandfield.about.com/od/longjump/qt/olymlongjumpmen.htm

Description

Hours of sleep for teenagers

Format

A data frame with 446 observations on the following 3 variables.

Person

Cased ID number

Age

Age (in years)

Outcome

Average at least 7 hours of sleep? (1=yes or 0=no)

Details

Data from a sample of 446 teens, aged 14 to 18, who answer the question, "On an average school night, how many hours of sleep do you get?" The outcome variable records whether or not each person averages at least 7 hours of sleep.

Source

Wahlstrom, K., Dretzke, B., Gordon, M., Peterson, K., Edwards, K., & Gdula, J. (2014) "Examining the Impact of Later School Start Times on the Health and Academic Performance of High School Students: A Multi-Site Study," Center for Applied Research and Educational Improvement. St Paul, MN: University of Minnesota.

Description

Which "lost" letters will be returned by the public?

Format

A data frame with 140 observations on the following 8 variables.

Details

In 1999 Grinnell College students Laurelin Muir and Adam Gratch conducted an experiment for an introductory statistics class. They intentionally "lost" 140 letters in either the city of Des Moines, the town of Grinnell, or on the Grinnell College campus. Half of each sample were addressed to Friends of the Confederacy and the other half to Iowa Peaceworks. The students kept track of which letters were eventually returned.

Source

Student project at Grinnell College

Description

Training records for a marathon runner

Format

A dataset with 1128 observations on the following 9 variables.

Details

Information from training records of a marathoner over a five-year period from 2002-2006.

Source

Data from training records of one of the Stat2 authors.

Description

Daily changes in two stock market indices

Format

A dataset with 56 observations on the following 5 variables.

Details

This dataset contains data on daily changes from two stock markets over 56 days from 06-Aug-09 to 02-Nov-09. The Dow Jones Industrial Average is based in New York and the Nikkei 225 is a stock index in Japan.

Source

Dow Jones Industrial Average:
http://markets.cbsnews.com/cbsnews/quote/historical?
Month=11&Symbol=310%3A998313&Year=2009&Range=12&tag=cbsnewsSectionsArea
Historical Nikkei 225 index:
http://markets.cbsnews.com/cbsnews/quote/historical?
Month=11&Symbol=992%3A1900000035&Year=2009&Range=12&tag=cbsnewsSectionsArea

Description

Semester enrollments in mathematics courses

Format

A dataset with 11 observations on the following 3 variables.

Details

Total enrollments in mathematics courses at a small liberal arts college were obtained for each semester from Fall 2001 to Spring 2012.

Source

The data were obtained from http://Registrar.Kenyon.edu on June 1, 2012.

Description

Results from a Math Placement exam at a liberal arts college

Format

A dataset with 2696 observations on the following 16 variables.

Details

Scores and course results for students taking a math placement exam at a college.

Source

Personal correspondence

Description

Medical school admission status and information on GPA and standardized test scores

Format

A dataset with 55 observations on the following 11 variables.

Details

This dataset has information gathered on 55 medical school applicants from a liberal arts college in the Midwest.

Source

Data collected at a midwestern liberal arts college.

Description

Comparing meniscus repair methods on cadaver knees

Format

A data frame with 18 observations on the following 4 variables.

Method

Meniscus repair method (1 = Vertical Suture, 2 = Meniscus Arrow, 3 = FasT-Fix)

FailureLoad

Load at failure (in Newtons)

Displacement

Displacement (in mm)

Stiffness

Stiffness (Newtons/mm)

Details

Eighteen, lightly embalmed, cadaveric knee specimens were used in a study to compare three different methods of meniscus repair. The specimens were randomly assigned to one of the three treatments: vertical suture, meniscus arrow, FasT-Fix. They were evaluated on three different response variables: load at failure, stiffness, and displacement.

Source

P. Borden, J. Nyland, D.N.M. Caborn, D. Pienkowski (2003), "Biomechanical Comparison of the FasT-Fix Meniscal Repair Suture System with Vertical Mattress Sutures and Meniscus Arrows," The American Journal of Sports Medicine, Vol. 31, #3, pp. 374-378

Dataset downloaded from http://www.stat.ufl.edu/~winner/data/meniscus.txt

Description

Admissions to a mental health emergency room and full moons

Format

A dataset with 36 observations on the following 3 variables.

Details

Some researchers in the early 1970s set out to study whether there is a "full-moon" effect on emergency room admissions at a mental health hospital. They separated the data over 12 months into rates before the full moon (mean number of patients seen 4-13 days before the full moon), during the full moon (the number of patients seen on the full moon day), and after the full moon (mean number of patients seen 4-13 days after the full moon).

Source

Introduction to Mathematical Statistics and its Applications by Richard J. Larsen and Morris L. Marx. Prentice Hall:Englewood Cliffs, NJ, 1986.

References

The original discussion of the study is in Blackman, S., and Catalina, D. (1973). "The moon and the emergency room." Perceptual and Motor Skills 37, 624-626.

Description

Body size and metabolic rate of Manduca Sexta caterpillars

Format

A dataset with 305 observations on the following 7 variables.

Details

Marisa Stearns collected and analyzed body size and metabolic rates for Manduca Sexta caterpillars.

Source

We thank Professor Itagaki and his research students for sharing these data.

Description

Commute times for four cities

Format

A data frame with 2000 observations on the following 3 variables.

City

Boston, Houston, Minneapolis, or Washington

Distance

Distance of commute (in miles)

Time

Time of commute (in minutes)

Details

The data are distances (miles) and times (minutes) of daily commute (one-way) for random samples of 500 commuters in each of four cities (Boston, Houston, Minneapolis, Washington) in 2007. The random samples were taken from the Metropolitan Public Use File of the 2007 American Housing Survey

Source

2007 American Housing Survey https://www.census.gov/programs-surveys/ahs/data/2007/ahs-2007-public-use-file–puf-.html

Description

Health services data for 83 metropolitan areas

Format

A dataset with 83 observations on the following 16 variables.

Details

The U.S. Census Bureau regularly collects information for many metropolitan areas in the United States, including data on number of physicians and number (and size) of hospitals. This dataset has such information for 83 different metropolitan areas.

This dataset is in the first edition, but replaced by CountyHealth in the second edition.

Source

U.S. Census Bureau: 2006 State and Metropolitan Area Data Book (Table B-6)
http://www.census.gov/prod/2006pubs/smadb/smadb-06.pdf

Description

Effects of transcranial magnetic stimulation (TMS) on migraine headaches

Format

A data frame with 2 observations on the following 4 variables.

Group

Treatment group (Placebo or TMS)

Yes

Count of number of patients that were pain-free in each group

No

Count of number of patients that had pain in each group

Trials

Number of patients in each group

Details

A study investigated whether a handheld device that sends a magnetic pulse into a person's head might be an effective treatment for migraine headaches. Researchers recruited 200 subjects who suffered from migraines and randomly assigned them to receive either the TMS (transcranial magnetic stimulation) treatment or a sham (placebo) treatment from a device that did not deliver any stimulation. Subjects were instructed to apply the device at the onset of migraine symptoms and then assess how they felt two hours later. This dataset is a two-way table of the results.

This dataset was called TMS in the first edition.

Source

Based on results in R. B. Lipton, et al, (2010) "Single-pulse Transcranial Magnetic Stimulation for Acute Treatment of Migraine with Aura: A Randomised, Double-blind, Parallel-group, Shamcontrolled Trial," Lancet Neurology, 9(4):373-380.

Description

Attitudes towards ethics of a famous Milgram experiment

Format

A dataset with 37 observations on the following 2 variables.

Details

One of the most famous and most disturbing psychological studies of the twentieth century took place in the laboratory of Stanley Milgram at Yale University. Milgram's subjects were asked to monitor the answers of a "learner" and to push a button to deliver shocks whenever the learner gave a wrong answer. The more wrong answers, the more powerful the shock. Even Milgram himself was surprised by the results: Every one of his subjects ended up delivering what they thought was a dangerous 300-volt shock to a slow "learner" as punishment for repeated wrong answers.

Even though the "shocks" were not real and the "learner" was in on the secret, the results triggered a hot debate about ethics and experiments with human subjects. To study attitudes on this issue, Harvard graduate student Maryann de Mateo conducted a randomized comparative experiment. Her subjects were 37 high school teachers who did not know about the Milgram study. Using chance, Maryann assigned each teacher to one of three treatment groups:

Group 1: Actual results. Each subject in this group read a description of Milgram's study, including the actual results that every subject delivered the highest possible "shock."

Group 2: Many complied. Each subject read the same description given to the subjects in Group 1, except that the actual results were replaced by fake results, that many but not all subjects complied.

Group 3. Most refused. For subjects in this group, the fake results said that most subjects refused to comply.

After reading the description, each subject was asked to rate the study according to how ethical they thought it was, from 1 (not at all ethical) to 9 (completely ethical.)

Source

"An experimental study of attitudes toward deception" by Mary Ann DiMatteo. Unpublished manuscript, Department of Psychology and Social Relations, Harvard University (1972).

Description

Data for Major League Baseball teams from the 2007 regular season

Format

A dataset with 30 observations on the following 21 variables.

Details

Data for all 30 Major League Baseball (MLB) teams for the 2007 regular season. This includes team batting statistics (BattingAvg through SLG) and team pitching statistics (ERA through WHIP)

Updated to MLBStandings2016 in second edition.

Source

Data downloaded from baseball-reference.com:
http://www.baseball-reference.com/leagues/MLB/2007-standings.shtml
http://www.baseball-reference.com/leagues/MLB/2007.shtml

Description

Major League Baseball (MLB) standings and team statistics for the 2016 season

Format

A data frame with 30 observations on the following 21 variables.

Team

Team name

League

AL=American or NL=National

Wins

Number of wins for the season (out of 162 games)

Losses

Number of losses for the season

WinPct

Proportion of games won

BattingAverage

Team batting average

Runs

Number of runs scored

Hits

Number of hits

HR

Number of home runs hit

Doubles

Number of doubles hit

Triples

Number of triples hit

RBI

Number of runs batted in

SB

Number of stolen bases

OBP

On base percentage

SLG

Slugging percentage

ERA

Earned run average (earned runs allowed per 9 innings)

HitsAllowed

Number of hits against the team

Walks

Number of walks allowed

StrikeOuts

Number of strikeouts (by the team's pitchers)

Saves

Number of games saved (by the team's pitchers)

WHIP

Number of walks and hits per inning pitched

Details

Data for all 30 Major League Baseball (MLB) teams for the 2016 regular season. This includes team batting statistics (BattingAvg through SLG) and team pitching statistics (ERA through WHIP)

Source

Data downloaded from baseball-reference.com:
http://www.baseball-reference.com/leagues/MLB/2016-standings.shtml
http://www.baseball-reference.com/leagues/MLB/2016.shtml

Description

Body size and eggs produced for a species of moths

Format

A dataset with 39 observations on the following 2 variables.

Details

Researchers were interested in an association between body size and the number of eggs produced by a species of moths.

Source

We thank Professor Itagaki and his students for sharing this data from experiments on Manduca Sexta.

Description

Effects of altering serotonin levels on social interactions of mice

Format

A data frame with 48 observations on the following 3 variables.

Contacts

Number of social contacts the mouse had during the experiment

Sex

F=female or M=male

Genotype

Minus, Mixed, or Plus (see description below)

Details

Serotonin is a chemical that influences mood balance in humans. But how does it affect mice? Scientists genetically altered mice by "knocking out" the expression of a gene, tryptophan hydroxylase 2 (Tph2), that regulates serotonin production. With careful breeding, the scientists produced three types of mice that we label as “Minus” for Tph2-/-, “Plus” for Tph2+/+, “Mixed” for Tph2+/-. The variable Genotype records Minus/Plus/Mixed. The variable Contacts is the number of social contacts that a mouse had with other mice during an experiment and the variable Sex is “M” for males and “F” for females.

Source

Beis D, Holzwarth K, Flinders M, Bader M, Wohr M, Alenina N., (2015) "Brain serotonin deficiency leads to social communication deficits in mice," Biol. Lett. 11:20150057.
http://dx.doi.org/10.1098/rsbl.2015.0057

Once you go to the above link, to get the data, click on the "Figures and Data" tab. Then click on the "Juvenile SocInter Behavior Data" link to download a hairy data file that needs to be cleaned a great deal to get our data.

Description

Estimates of 45 seconds with different music playing

Format

A data frame with 60 observations on the following 6 variables.

MusicBg

Music playing in the background (no or yes)

Subject

Code for each subject (subj1 through subj20)

Sex

Subject's sex (f=female or m=male)

TimeGuess

Subject's time estimating 45 seconds (in seconds)

Music

Type of music (calm, control, or upbeat)

Accuracy

Absolute value of TimeGuess minus 45

Details

Participants were asked to judge when 45 seconds had passed in silence (control), while listening to an upbeat song (Metropolis, by David Guetta and Nicky Romero), and while listening to a calm song (Bach's Das Wohltemperierte Klavier, Prelude in C Major). The order in which the three conditions were experienced was randomized for each participant. Time until subject guessed 45 seconds had elapsed (TimeGuess) and the magnitude of the difference from 45 (Accuracy) were recorded.

Source

Data collected by Ksenia Vlasov at Oberlin College.

Description

Data from births in North Carolina in 2001

Format

A dataset with 1450 observations on the following 15 variables.

Details

This dataset contains data on a sample of 1450 birth records that statistician John Holcomb selected from the North Carolina State Center for Health and Environmental Statistics.

Source

Thanks to John Holcomb at Cleveland State University for sharing these data.

Description

Standings for National Football League teams in 2007

Format

A dataset with 32 observations on the following 10 variables.

Details

Data for all 32 National Football League (NFL) teams for the 2007 regular season.

Updated to NFLStandings2016 in the second edition.

Source

Data downloaded from www.nfl.com

Description

Standings and team statistics for National Football League (NFL) teams in the 2016 season

Format

A data frame with 32 observations on the following 11 variables.

Team

Team name

Wins

Wins in the 2016 regular season (out of 16 games)

Losses

Losses in the 2016 regular season

Ties

Ties in the 2016 regular season (ties are very rare in the NFL)

WinPct

Winning percentage = (Wins+0.5*Ties)/16 games

PointsFor

Points scored

PointsAgainst

Points allowed

NetPts

Points scored minus Points allowed

YardsFor

Offensive yards gained by the team

YardsAgainst

Offensive yards against the team

TDs

Touchdowns scored

Details

Standings for the 2016 regular season of the National Football League (NFL) along with points and scored and allowed for each team in its16 games.

Source

Data downloaded from:
http://www.pro-football-reference.com/years/2016/

Description

Characteristics of nursing homes in New Mexico.

Format

A dataset with 52 observations on the following 7 variables.

Details

The data were collected by the Department of Health and Social Services of the State of New Mexico and cover 52 of the 60 licensed nursing facilities in New Mexico in 1988.

Source

Downloaded from DASL at http://lib.stat.cmu.edu/DASL/Datafiles/Nursingdat.html

References

Howard L. Smith, Niell F. Piland, and Nancy Fisher, "A Comparison of Financial Performance, Organizational Characteristics, and Management Strategy Among Rural and Urban Nursing Facilities," Journal of Rural Health, Winter 1992, pp 27-40.

Description

Experiment to measure the effect of ultrasound on deapsorbing oil from sand

Format

A data frame with 40 observations on the following 4 variables.

Salt

Type of water (1=salt water or 0=distilled water)

Ultra

Amount of time each sample was exposed to ultrasound (5 or 10 minutes)

Oil

Amount of oil in the sample (5ml or 10 ml)

Diff

Difference in the amount of oil removed between the ultrasound run and an equivalent control run (no ultrasound) (Diff = Treatment - Control)

Details

This data set is the result of a science fair experiment run by a high school student. The basic question was whether exposing sand with oil in it (think oil spill) to ultrasound could help the oil deapsorb from it better than sand that was not exposed to ultrasound. There were two levels of ultrasound tested (5 minutes and 10 minutes) and two levels of oil (5 ml and 10 ml). There was also a question of whether exposure to salt water or fresh water made a difference so half the samples had salt water, the others distilled water. Each combination of factor levels was replicated 5 times. There were also an equivalent number of control observations run, all factors being the same but without any exposure to ultrasound. Each experimental run was paired with an appropriate control run and the response variable is the difference in the amount of oil removed in the experimental run and the control run.

Source

Experiment run by Las Vegas high school student Chris Mathews for a science fair project in spring 2016.

Description

Measurements of the pesticide fenthion in olive oil over time

Format

A dataset with 18 observations on the following 7 variables.

Details

Fenthion is a pesticide used against the olive fruit fly in olive groves. It is toxic to humans so it is important that there be no residue left on the fruit or in olive oil that will be consumed. One theory was that if there is residue of the pesticide left in the olive oil, it would dissipate over time. Chemists set out to test that theory by taking a random sample of small amounts of olive oil with fenthion residue and measuring the amount of fenthion in the oil at three different times over the year - day 0, day 281 and day 365.

Source

Data provided by Rosemary Roberts and discussed in "Persistence of fenthion residues in olive oil" by Chaido Lentza-Rizos, Elizabeth J. Avramides, and Rosemary A. Roberts in Pest Management Science, Vol. 40, Issue 1, Jan. 1994, pp. 63-69.

Description

Number of damaged O-rings on space shuttle launches and launch temperature

Format

A dataset with 24 observations on the following 2 variables.

Details

The space shuttle Challenger exploded shortly after liftoff in 1987. The subsequent investigation focused on the failure of O-ring seals, which allowed liquid hydrogen and oxygen to mix and explode. These failures might be related to temperature at the launch site which was near freezing (32 degrees F) on that day. This dataset shows the number of O-ring failures on previous shuttle launches, along with an indicator for whether the temperature was above or below 65 degrees F.

Source

Data can be found in "Risk analysis of the space shuttle: Pre-challenger prediction of failure" by Siddhartha R. Dalal, Edward B. Fowlke, and Bruce Hoadley in Journal of the American Statistical Association, Vol. 84, No. 408 (Dec. 1989), pp 945-957

Description

Survey of college students to took at factors related to having overdrawn a checking account.

Format

A dataset with 450 observations on the following 4 variables.

Details

Researchers conducted a survey of 450 undergraduates in large introductory courses at either Mississippi State University or the University of Mississippi. There were close to 150 questions on the survey, but only four of these variables are included in this dataset. (You can consult the paper to learn how the variables beyond these 4 affect the analysis.) The primary interest for the researchers was factors relating to whether or not a student has ever overdrawn a checking account.

Renamed as CreditRisk in second edition.

Source

Worthy S.L., Jonkman J.N., Blinn-Pike L. (2010), "Sensation-Seeking, Risk-Taking, and Problematic Financial Behaviors of College Students," Journal of Family and Economic Issues, 31: 161-170

Description

Comparing methods for measuring the size of oysters

Format

A data frame with 30 observations on the following 5 variables.

ID

ID number of each oyster

Weight

Weight (in grams)

Volume

Volume (in cubic centimeters)

ThreeD

Measurement from a 3D system (pixels)

TwoD

Measurement from a 2D cross-section (pixels)

Details

In 2001 engineers at an R&D lab Agri-Tech, Inc, in Woodstock, Virginia, designed a 3-D system that they hoped would improve on the existing 2-D system for measuring the size of oysters. The 3-D system used computer scanning to estimate an oyster volume, whereas the old 2-D system estimated a cross-sectional area. Data shows the result of both systems, as well as the actual weight and volume of each oyster used in calibration.

Source

Data found at JSE data archive: http://ww2.amstat.org/publications/jse/jse_data_archive.htm with the filenames of 30oysters. Contributors are G. Andy Chang, G. Jay Kerns, D. J. Lee, and Gary L. Stanek.

Original article is: Lee, D., Lane, R., and Chang, G., (2001) "Three-dimension Reconstruction for High-speed Volume Measurement," Proceedings of the International Society for Optical Engineering, Machine Vision and Three-Dimensional Imaging Systems for Inspection and Metrology, Volume 4189, p.258-267.

Description

Votes for Geroge Bush and Pat Buchanan in Florida counties for the 2000 U.S. presidential election

Format

A dataset with 67 observations on the following 3 variables.

Details

The race for the presidency of the United States in the fall of 2000 was very close, with the electoral votes from Florida determining the outcome. In the disputed final tally in Florida, George W. Bush won by just 537 votes over Al Gore, out of almost 6 million votes cast. About 2.3% of the votes cast in Florida were awarded to other candidates. One of those other candidates was Pat Buchanan, who did much better in Palm Beach County than he did anywhere else. Palm Beach County used a unique "butterfly ballot" that had candidate names on either side of the page with "chads" to be punched in the middle. This non-standard ballot seemed to confuse some voters, who punched votes for Buchanan that may have been intended for a different candidate. This dataset shows the number of votes for Bush and Buchanan in each Florida county.

Source

Florida county data for the 2000 presidential election can be found at
http://election.dos.state.fl.us/elections/resultsarchive/Index.asp?ElectionDate=11/7/00

Description

Monthly traffic (in 1,000's) across the Peace Bridge between Canada and the U.S.

Format

A data frame with 156 observations on the following 4 variables.

Year

Year (2003 to 2015)

Month

Month (1 to 12)

Traffic

Vehicles (in 1,000's)

t

Time frame (1 to 156)

Details

Monthly traffic (in thousands of vehicles) across the Peace Bridge between the U.S. and Canada near Niagara Falls between January 2003 and December 2015. Note PeaceBridge2012 has only the last four years of this series.

Source

http://www.peacebridge.com/index.php/historical-traffic-statistics/yearly-volumes

Description

Monthly traffic (in 1,000's) across the Peace Bridge between Canada and the U.S.

Format

A data frame with 48 observations on the following 4 variables.

Year

Year (2012 to 2015)

Month

Month (1 to 12)

Traffic

Vehicles (in 1,000's)

t

Time frame (1 to 48)

Details

Monthly traffic (in thousands of vehicles) across the Peace Bridge between the U.S. and Canada near Niagara Falls between January 2012 and December 2015. Note PeaceBridge2003 has similar data starting in 2003.

Source

http://www.peacebridge.com/index.php/historical-traffic-statistics/yearly-volumes

Description

Daily walking amounts recorded on a personal pedometer from September-December 2011

Format

A dataset with 68 observations on the following 8 variables.

Details

A statistics professor regularly keeps a pedometer in his pocket. It records not only the number of steps taken each day, but also the number of steps taken at a moderate pace, the number of minutes walked at a moderate pace, and the number of miles total that he walked. He also added to the data set the day of the week, whether it was rainy, sunny, or cold (on sunny days he often biked, but on rainy or cold days he did not), and whether it was a weekday or weekend.

Source

One of the Stat2 authors

Description

Size of perch caught in a Finnish lake

Format

A dataset with 56 observations on the following 4 variables.

Details

This dataset comes from a sample of fish (perch) caught at Lake Laengelmavesi in Finland.

Source

JSE Data Archive, http://www.amstat.org/publications/jse/jse_data_archive.htm, submitted by Juha Puranen.

Description

Effects of additives to pig feed on weight gain

Format

A dataset with 12 observations on the following 3 variables.

Details

A scientist in Iowa was interested in additives to standard pig chow that might increase the rate at which the pigs gained weight. Two factors of interest were vitamin B12 and antibiotics. To perform the experiment, the scientist randomly assigned 12 pigs, three to each of the diet combinations (Antibiotic only, B12 only, both, and neither).

Source

Data are found in Statistical Methods by George W. Snedecor and William G. Cochran (1967). Ames, IA: The Iowa State University Press.

References

Original source is Iowa Agricultural Experiment Station (1952). Animal Husbandry Swine Nutrition Experiment No. 577.

Description

Data from pine seedlings planted in 1990

Format

A dataset with 1000 observations on the following 15 variables.

Details

This dataset contains data from an experiment conducted by the Department of Biology at Kenyon College at a site near the campus in Gambier, Ohio. In April 1990, student and faculty volunteers planted 1000 white pine (Pinus strobes) seedlings at the Brown Family Environmental Center. These seedlings were planted in two grids, distinguished by 10- and 15-foot spacings between the seedlings. Several variables were measured and recorded for each seedling over time (in 1990, 1996, and 1997).

Source

Thanks to the Kenyon College Department of Biology for sharing these data.

Description

Dopamine levels with different amounts of phenylalanine in diets

Format

A data frame with 20 observations on the following 4 variables.

Subject

Initials to identify each subject

Diet

Level of phenylalanine in diet (Low or Normal)

DietControl

Ability to follow prescribed diet (Good or Poor)

Y

Concentration of dopamine (micrograms per milligram of creatinine)

Details

Phenylketonuria (PKU) is an enzyme deficiency that keeps a person from being able to synthesize enough dopamine. The amino acid phenylalanine inhibits the enzyme needed to synthesize dopamine, and so to some extent, a diet low in phenylalanine can moderate the symptoms of PKU. In short, less phenylalanine in the diet should lead to more dopamine in the brain. The dopamine level for each patient was measured after a normal diet and after a week on a low phenylalanine diet.

Source

Krause, Halminski, McDonald, Dembure, Salvo, Freides, and Elsas (1985) "Biochemical and Neuropsychological Effects of Elevated Plasma Phenylalanine in Patients with Treated Phenylketonuria," J. of Clinical Investigation, Volume 75, January 1985, 40-48

Several of the values were altered slightly in ways that would not change the analysis except to simplify the arithmetic.

Description

Survey of political activity for Grinnell College students

Format

A dataset with 59 observations on the following 9 variables.

Details

Students Jennifer Wolfson and Meredith Goulet conducted a survey in the spring of 1992 of Grinnell College students to ascertain patterns of political behavior. They took a simple random sample of 60 students who were U.S. citizens and conducted phone interviews. Using several "call backs" they obtained 59 responses.

Source

Student survey at Grinnell College

Description

Polls for 2008 U.S. presidential election

Format

A dataset with 102 observations on the following 11 variables.

Details

The file Pollster08 contains data from 102 polls that were taken during the 2008 U.S. Presidential campaign. These data include all presidential polls reported on the internet site pollster.com that were taken between August 29th, when John McCain announced that Sarah Palin would be his running mate as the Republican nominee for vice president, and the end of September.

Source

Downloaded from pollster.com

Description

Unpopped kernels in bags of microwave popcorn

Format

A dataset with 12 observations on the following 3 variables.

Details

Two students, Lara and Lisa, conducted an experiment to compare Orville Redenbacher's Light Butter Flavor vs. Seaway microwave popcorn. They made 12 batches of popcorn, 6 of each type, cooking each batch for four minutes. They noted that the microwave oven seemed to get warmer as they went along so they kept track of six trials and randomly chose which brand would go first for each trial. For a response variable they counted the number of unpopped kernels and then adjusted the count for Seaway for having more ounces per bag of popcorn (3.5 vs 3.0).

Source

Student project

Description

Compare prices for Porsche and Jaguar cars offered for sale at an internet site

Format

A dataset with 60 observations on the following 5 variables.

Details

Two students collected samples of Porsche and Jaguar cars that were offered for sale at an internet site. In addition to asking price, they recorded the model year (converting to age) and mileage of each advertised car.

Source

Student project data collected from autotrader.com in Spring 2007.

Description

Prices for Porsche cars offered for sale at an internet site.

Format

A dataset with 30 observations on the following 3 variables.

Details

A student was interested in prices for used Porsche sports cars being sold on the internet. He selected a random sample of 30 Porsches from the ones being advertised at autotrader.com. For each car he recorded the asking price, mileage, and model year (which he converted to age).

This dataset was replaced by AccordPrice for second edition.

Source

Data collected for a student project from autotrader.com in February 2007.

Description

Pulse rates before and after exercise for a sample of statistics students

Format

A dataset with 232 observations on the following 7 variables.