2. Let's look at the North Carolina births data again. It is known that smoking during pregnancy can cause low-birthweight. Whether the mother is a smoker may confound the relationship between mothers' marital status and whether the babies have low birth weights. (a) The variable habit in the NC births data records whether the mother was a smoker or nonsmoker during pregnancy. Obtain the two-way contingency table between marital and habit. What per centage of married mothers smoked during pregnancy? How about unmarried mothers? Were married or unmarried mothers more likely to smoke during pregnancy? (b) Let's examine the relation of marital and lowbirthveight after adjusting for mothers' smoking habit. tab = table (nc$habit , nc$marital , nc$lowbirthweight) ftable (tab) prop .table (ftable (tab) , 1) 1. Consider babies with NONSMOKING mothers only, were those born to married mother or those born to unmarried mother more likely to have low birth weights? ii. Consider babies with SMOKING mothers only, were those born to married mother or those born to unmarried mother more likely to have low birth weights? iii. Is outofmarriage birth associated with low birth weights after adjusting for mothers' smoking habit? (c) Can you claim that marriage reduces the chance of births having low birth weights? 3. Smokers may have more difcult time quitting smoking if they live with another smoker. A study compar ing bupropion {an antidepressant and smoking cessation aid) with a placebo tried to take this into account in their design. The researchers rst split the subjects based on whether they lived with another smoker. The subjects who live with another smoker were randomly assigned to take bupropion or a placebo, and those who didn't live with smokers were also randomly assigned to take bupropion or a placebo. The gure below shows a ow chart of the design1 when 250 of the 429 study subjects lived with nonsmokers and 179 lived with another smoker. Not Li . with a f.- Bupropion (n = 125) H Smoker (n = 250) R. Placebo (n : 125) All Subjects: 429 Smokers ' B n = a Living with a far4 upIOplon ( 90) Smoker (n = 179) as... Placebo (n = 89) The percentages of subjects who relapsed were then compared among the four groups. (a) If the two groups of subjects that received bupropion had substantially lower relapse rates than the two placebo groups1 can we claim that bupropion is effective as a smoking cessation aid? (b) Has blocking been used in this study? If so, identify the blocks. (c) If the placebo group of subjects who lived with another smoker had a higher relapse rate than the placebo group of subjects who did not live with smokers1 can we claim that living with smoker(s) makes it harder to quit smoking? Why or why not? 4. A university classied its classes as either "small" (fewer than 40 students) or "large". A dean sees that 62% of Department A's classes are small1 while Department B has only 40% small classes. She wonders if she should cut Department A's budget and insist on larger classes. Department A responds to the dean by pointing out that classes for third and forthyear students tend to be smaller than classes for rst