An article in the magazine Science (Service, 1994) discussed a study comparing the health of 6000 vegetarians and a similar number of their friends and relatives who were not vegetarians. The vegetarians had a 28% lower death rate from heart attacks and a 39% lower death rate from cancer, even after the researchers accounted for differences in smoking, weight, and social class. In other words, the reported percentages were the remaining differences after adjusting for differences in death rates due to those factors.

a. Is this an observational study or a randomized experiment? Explain.

b. On the basis of this information, can we conclude that a vegetarian diet causes lower death rates from heart attacks and cancer? Explain.

c. Give an example of a potential confounding variable and explain what it means to say that it is a confounding variable.