NAME: eyecolorgenderdata.csv
TYPE: Survey
SIZE: 2068 observations, 14 variables
ARTICLE TITLE: Does Eye Color Depend on Gender? It Might Depend on Who or How
You Ask.
DESCRIPTIVE ABSTRACT:
Data on eye color and gender were collected from students enrolled in an introductory statistics
course at a large university over a recent four year period. Biologically, eye color and gender are
independent traits. However, in the data collected from our students, there is a statistically
significant dependence between the two variables.
SOURCES:
Data were collected as a part of an opening course survey from students enrolled in an
introductory statistics course at a large university over a recent four year period.
VARIABLE DESCRIPTIONS:
Data are comma delimited. Variables used in article are Gender (Female and Male) and Eye
Color (Blue, Brown, Green, Hazel, Other). Other variables included in data set are: Age (in
years); YearinSchool (First, Second, Third, Fourth, Other); Height (in inches); Miles (distance
from home town of student to Ames, IA); Brothers (number of brothers); Sisters (number of
sisters); CompTime (number of hours spent on computer per week); Exercise (whether the student
exercises Yes or No); ExerTime (number of hours spent exercising per week); MusicCDs (number of
music CDs student owns); PlayGames (number of hours spent playing games per week); WatchTV (number
of hours spent watching TV per week).
STORY BEHIND THE DATA:
In order to increase student interest and to obtain real data for use in the introductory statistics
course, student level data, including eye color and gender, were collected as a part of an opening
course survey. Biologically, gender and eye color are independent traits. However, in this
population, the two variables are statistically dependent.
PEDAGOGICAL NOTES:
If treated as a representative sample from a larger population, this data set can be used to
illustrate concepts such as conditional distributions, populations, samples and sampling
variability, and tests of independence. Alternatively, considering the data as the population of
interest, this example can be used to illustrate probability rules based on selecting a student at
random from the population.
SUBMITTED BY:
Amy G. Froelich
Department of Statistics
Iowa State University
3109 Snedecor Hall
Ames, IA 50011-1210
amyf@iastate.edu
W. Robert Stephenson
Department of Statistics
Iowa State University
3111 Snedecor Hall
Ames, IA 50011-1210
wrstephe@iastate.edu