Datasets for Statistical Analysis: One- and two-sample data

• Welcome
• Datasets from books
• Techniques index
  • time series
  • regression
  • generalized linear models
  • multivariate analysis
  • designed experiments
  • one- and two-sample data
• Applications index
• Reported statistics

• One-sample data
• Two-sample data
  • Two independent samples
  • Two paired samples

One-sample data

• AFL Football Department spending and results
  Spending of AFL clubs compared to performance
• Properties of bamboo flooring
  Moisture content, stiffness, bending strength and hardness of five samples of bamboo flooring
• Drivers by Zodiac sign
  The percent of car crashes for most States and Territories of Australia (and national figures) by Zodiac sign. There is no association despite a claim in the Australian newspaper.
• Baby births in one 24-hour period from Brisbane Mater Hospital
  This dataset can be used to demonstrate the binomial, Poisson, geometric, exponential and normal distributions.
• Counting alpha-particles
  A Poisson distribution fits the data nicely.
• Flying bomb hits on London during World War II
  A Poisson distribution fits the data nicely.
• Height and resting pulse
  The heights and resting pulses for a sample of hospital patients. Both are almost normally distributed.
• Intervals between vehicles
  The data might be expected to follow an exponential distribution, but do not.
• Software system failures
  The data appear well modelled by an exponential distribution
• New York tornados
  The data are modelled moderately well by a Poisson distribution.
• Numbers drawn in Oz Lotto
  The number of times each number from 1 to 45 has been drawn in Oz Lotto from Game 1 to Game 473.
• Nerve impulse times
  The data are well modelled by an exponential distribution
• Height and weight of eleven years old girls
  The heights and weights of eleven year old girls;
• Forearm lengths
  The forearm length of 140 adult males; a normal distribution fits the data well.
• Amusement ride fatalities
  The number of fatalities at amusements rides in the United States, 1987 to 2004
• Weight of Cherry Ripe mini-bars
  The weight of 12 individually wrapped Cherry Ripe chocolate bars, meant to weight 18g on average

Two-sample data

Two independent samples

• Neural tube defects
  The number of neural tube defects per 10 000 births for England and Wales for every two years between 1977 and 1985 inclusive.
• Broad bean plants
  Can be used for a two-sample t-test, but plot the data first!
• Estimating lengths
  Estimates of the length of a room in metres and in feet (unpaired).
• Whisky prices
  Whisky prices in 1991 in the USA for 16 monopoly states and 26 private-ownership states
• Salaries in two occupations
  The salaries from 72 randomly chosen jobs ads in The Guardian on April 6, 1992 in pounds sterling.
• Tomatos yields
  The yield of tomatoes using two different fertilizers. A good small example.
• Height and weight of eleven years old girls
  The heights and weights of eleven year old girls;
• Caesarean in Canadian hospitals
  The data give the number of births in Ontario, Canada, from 1982/83 to 1991/92, and the number of caesarean section in the same years. The data can be used for a two-sample test of proportions for two years.

Two paired samples

• Hardness of bamboo flooring
  A small experiment (5 samples; two reps) to measure the hardness of bamboo flooring
• Bouncing squash balls
  Squash balls are bounced at room temperature and after being submerged in boiling water
• Fingers ridges on identical twins
  The number of fingers ridges on identical twins. The within-sibling variation is small, while the between sibling variation is much larger.
• Statures of brother and sister
  The heights of 11 pairs of brothers and sisters.
• Brisbane Lions AFL club
  The data give the weights of the eleven Brisbane Bears (an Australian Rules Football club)) players who played in the 1995 finals series and also the 2002 premiership flag team.
• Hospital admissions and discharges
  The admissions are uniform; the discharges show people leaving on Friday, and fewer on weekends.
• Toowoomba fuel prices
  The monthly average price of unleaded and LRP fuel in Toowoomba, Qld, Australia. A paired test shows definite differences, but a non-paired test does not.
• SMS speed
  The speed at which people can SMS a message; paired (within age groups, using own and control phones) and non-paired tests (teens versus over 30s) are possible.