| Filename |
Description |
Questions to ask the data |
Codebook |
Source |
| twomarathons.txt twomarathons.dta |
Finishing times for two
marathons: the 2004 Olympics in Athens and a public marathon held in
2004 in London, Ontario, Canada. Basic unit is the runner, and a
categorical variable indicates the event and another the gender. |
Before looking at the data,
which marathon will have the most variability? Do men have more
variability than women? What shape should the distributions have
and how will this change depending on whether we look at genders
separately, marathong separately? |
Olympic Data comes from NBCs
olympic site. Ontario marathon data comes from |
|
| wlarealestate.txt wlarealestate.dta |
Data on recent home sales
(August 2004) in two neighborhoods in Los Angeles. Cost, square
footage, age, number of bedrooms. |
What's shape of
distribution? Is a mean a good description? A median?
What's relation between number of bedrooms and price? |
||
| aaup.txt aaup.dta |
Average salary at a number of
colleges/universities in 1994. |
Used for ASA graphics
competition. Questions about variation, changes with rank,
relations between salaries, and variation with respect to region of
country. Can be used to test data management skills, as it
contains missing values and some coding must be done to put states in
geographical regions. |
aaup.txt |
AAUP (American Association
of University Professors) 1994 Salary Survey which appeared in the March-April 1994 issue of Academe. |
| usnews.txt usnews.dta |
Tuituion and measures of quality
of a number of colleges and universities, from US News and World
Report. |
Used for ASA graphics
competition. Questions about predicting tuition based on various
factors, as well as comparisons between certain schools and regions. |
usnews.doc |
US News and World |