The Laws of Probability

Demonstrations > Drug Trials

FAQ

Questions about Strong Stuff: How effective is Viagra?

1. Why did you assume that 25% of Viagra users who gained no physical benefit from the drug nonetheless perceived that it helped them?

The controlled trials indicated that 25% of those who took sugar pills reported improvement in sexual function. For those who did not physically benefit from Viagra, the drug effectively functioned as a sugar pill. It is reasonable to infer that the rate at which they reported improvement was the same as for actual sugar pill users, namely, 25%.

2. Why say that Viagra has a 73% success rate rather than 80%? Even if 7% of users benefited psychologically rather than physically, should they be counted as having gained from Viagra?

Interesting point, but it is possible that psychological benefits, unlike physical benefits, might prove temporary. One could say that 73% is a conservative estimate of the success rate, and that an estimate between 73% and 80% could also be defended.

3. Didn’t FDA rules require Pfizer to report the results of the controlled experiment as it did (4/5 vs. 1/4)?

I have been told that this is the case. But perhaps Pfizer could have added some supplementary text indicating that, based on all the test results, an estimated 73% of users benefited physically, and another 7% either benefited from “mind over matter” or got better on their own.

-What is the placebo effect?
-How is the placebo effect calculated?

The Center for Experimental Pharmacology and Therapeutics, Harvard-MIT Division of Health Sciences and Technology is solely responsible for the content of this web course.