Investigation 8: Catnip aggression (due Thur, Feb 9)

You may work with one other person on this assignment, handing in one report with both names.  Word-processed reports are preferred to hand-written ones.  Please copy/paste relevant, well-labeled Minitab output into a Word file as appropriate.

A volunteer at an animal hospital investigated the effect of catnip on cats. She recorded the number of “negative interactions” that each cat engaged in during 15-minute time periods, immediately before and after being given a teaspoon of catnip. The data appear in the following table:

Cat name	Negative interactions before catnip	Negative interactions after catnip
Amelia	0	0
Bathsheba	3	6
Boris	3	4
Frank	0	1
Jupiter	0	0
Lupine	4	5
Madonna	1	3
Michelangelo	2	1
Oregano	3	5
Phantom	5	7
Posh	1	0
Sawyer	0	1
Scary	3	5
Slater	0	2
Tucker	2	2

a) Explain how you know that these data came from a matched-pairs rather than an independent-samples design.

b) Conduct a paired t-test of whether these sample data provide evidence that cats’ negative interactions differ before/after receiving catnip. Report the hypotheses, test statistic, and P-value. (Feel free to use Minitab to do the calculations. You will have to enter the data yourself, but you do not need to enter the cats’ names.) Summarize your conclusion.

c) Produce a 90% confidence interval for the population mean difference in negative interactions before/after catnip. Also write a sentence interpreting the interval.

d) List the technical conditions required for this t-test and t-interval to be valid. Investigate and comment on whether they appear to be met in this situation.

e) Suppose that an independent-samples design had produced exactly the same data. Re-analyze the data (i.e., answer questions b) and c) again) using an independent-samples analysis.

f) Comment on how your analysis reveals that the matched-pairs design was useful in this situation.