(This article was originally published at Statistical Modeling, Causal Inference, and Social Science, and syndicated at StatsBlogs.)
Brad Stiritz writes:
I thought you might enjoy reading the following Der Spiegel interview with Peter Wilmshurst. Talk about fighting the good fight! He took the path of greatest resistance, and he beat what I presume are pretty stiff odds.
Then the company representatives asked me to leave some of the patients out of the data analysis. Without these patients, the study result would have been positive.
I guess Serpico-esque stories like this are probably outlier stories, particularly when they have happier endings than what Frank Serpico experienced. Or for that matter, Boris Kolesnikov.
Wow—that’s pretty scary! I had cardiac catheterization once!
The Spiegel interview begins with a bang:
SPIEGEL: In your early years as a researcher, a pharmaceutical company offered you a bribe equivalent to two years of your salary: They wanted to prevent you from publishing negative study results. Were you disappointed that you weren’t worth more?
Peter Wilmshurst: (laughs) I was just a bit surprised to be offered any money, really. I was a very junior researcher and doctor, only 33 years old, so I didn’t know that sort of thing happened. I didn’t know that you could be offered money to conceal data.
SPIEGEL: How exactly did they offer it to you? They probably didn’t say: “Here’s a bribe for you.”
Wilmshurst: No, of course not! Initially we were talking about the results that I’d obtained: That the drug that I had been testing for them did not work and had dangerous side effects. Then the company representatives asked me to leave some of the patients out of the data analysis. Without these patients, the study result would have been positive. When I said I couldn’t do that, they asked me not to publish the data. And to compensate me for the work I had done in vain, they said, they would offer me this amount of money.
I recommend you read the whole thing.
P.S. Full disclosure: Some of my research is funded by Novartis.
The post “Positive Results Are Better for Your Career” appeared first on Statistical Modeling, Causal Inference, and Social Science.
Please comment on the article here: Statistical Modeling, Causal Inference, and Social Science
