Assignment III for Biostats Course VHM 801 at AVC - Winter semester 2026

The assignment is worth 10% of the final course mark. Please be aware that by handing in the home assignment you implicitly acknowledge to have read and accepted the instructions for home assignments as described on the VHM 801 homepage.

The data for the assignment were collected in a study at a veterinary hospital. Some owners of cats submitted to the hospital were selected to fill out a questionnaire about their cat. We concentrate here on two questions: the level of exercise (low/high) (of the cat!) and the amount of dry feed (little/much) given to the cat. For both questions, the two possible answers were suitably defined in quantitative terms. Two sets of questionnaire data were collected, one for 50 castrated male cats with diseases of the urinary system, and one for another group of 24 castrated male cats submitted to the hospital for routine treatments not related to such diseases. The data are given in the table below.

Cats with urinary diseasesCats without urinary diseases
Exercise levelExercise level
Amount of dry feedlowhighlowhigh
little53125
much142852

Files containing the complete data (including also the additional data described under 4. below) are available in Minitab format and also in comma-separated format, for import into Stata and other statistical software.

All three questions below should be answered. The same principles for documenting and discussing your analyses as in previous assignments apply. In particular, all statistical models and assumptions should be specified, and any specific conditions needed to apply the methods used should be discussed.

  1. For the cats with urinary diseases, examine whether any association between the cat's feed and exercise exist. If so, describe its nature; if not, summarize the feed and exercise answers separately. Compute relevant proportions in the respective distributions, and make sure to include confidence intervals for all parameters you estimate. Carry out a similar analysis for the cats without urinary diseases, and compare the results qualitatively (i.e., without carrying out any extra analysis) between the two groups.

  2. Analyze the full dataset to compare the set of questionnaire answers (on both questions) between the two groups of cats. Describe any significant (statistically/biologically) differences that may be seen between the two groups.

  3. To motivate the final analyses requested, statistical methods beyond this course ("log-linear models") can be applied to these data to justify separate analyses of the relationship between the cat's group (presence or absence of urinary disease) and each of the two questions (feed, exercise). For example, we can examine the relationship between feed and cat groups without taking the exercise into account. Carry out such an analysis for both the feed and exercise questions, and describe any significant (statistically/biologically) relationships that may be found.

Henrik Stryhn (hstryhn@upei.ca) 2026-03-13