Question 2

a) The variable geneXYZ denotes the activity of a gene, and smoke denotes the smoking status of individuals. Using a permutation approach or otherwise (justify your approach) is there evidence that the activity of the gene is higher in smokers than non-smokers?

b) Construct an 95% confidence interval for the difference in means using a simple bootstrap approach.

c) The smoke2 variable extends the smoke variable, splitting smokers into occasional and regular smokers. What is the F-statistic for the comparison of geneXYZ across the smoke2 groups? (assuming equal variances)