Many people believe that there is a "Friday effect" in the stock market. They don't necessarily spell out exactly what they mean by this, but there

is a sense that stock prices tend to be lower on Fridays than on other days. Because stock prices

are readily available on the Web, it should be fairly easy to test this (alternative) hypothesis empirically. Before collecting data and running a test, however, you must decide exactly which hypotheses you

want to test because there are several possibilities. Formulate at least two sets of null/alternative hypotheses. Then gather some stock price data and test your hypotheses. Can you conclude that there is a statistically significant Friday effect in the stock market?




9.3

For years, the drug Vioxx, developed and marketed by Merck, was one of the blockbuster drugs on the market. One of a number of

so-called Cox-2 anti-inflammatory drugs, Vioxx

was considered by many people a miracle drug for alleviating the pain from arthritis and other painful afflictions. Vioxx was marketed heavily on television, prescribed by most physicians, and used by an estimated two million Americans. All of that changed in October 2004, when the results of a large study were released. The study, which followed approximately 2600 subjects over

a period of about 18 months, concluded that Vioxx use over a long period of time caused a significant increase in the risk of developing serious heart problems. Merck almost immediately pulled Vioxx from the American market and doctors stopped prescribing it. On the basis of the study, Merck faced not only public embarrassment but the prospect of huge financial losses.

More specifically, the study had 1287 patients use Vioxx for an 18-month period, and it had another 1299 patients use a placebo over the same period. After 18 months, 45 of the Vioxx patients had developed serious heart problems, whereas only 25 patients on the placebo developed such problems.

Given these results, would you agree with the conclusion that Vioxx caused a significant increase in the risk of developing serious heart problems? First, answer this from a purely statistical point of view, where significant means statistically significant. What hypothesis should you test, and how should you run the test? When you run the test, what is the corresponding p-value? Next, look at it from the point of view of patients. If you were a Vioxx user, would these results cause you significant worry? After all, some of the subjects who took placebos also developed heart problems, and 45 might not be considered that much larger than 25. Finally, look

at it from Merck's point of view. Are the results practically significant to the company? What does it stand to lose? Develop an estimate, no matter how wild it might be, of the financial losses Merck might incur. Just think of all of those American Vioxx users and what they might do.