Wharton Prof's Statistical Sleuthing Leads to Resignation of Dutch Marketing Professor

These days everyone is a self-described skeptic or skep-something, but the Wharton School's Uri Simonsohn looks like the real deal.

Science has identified him as a "whistle blower" who smelled something fishy in the work of Dutch marketing professor Dirk Smeesters. Smeesters had authored a number of papers with headline-grabbing, counterintuitive findings on things like the effects of seeing the colors red and blue on stereotyping. Now it looks like those findings were counterintuitive because they weren't true.

Simonsohn's analysis led to an internal investigation and the Dutch researcher's resignation.

The Wharton whistle-blower had just been featured on the front page of The Inquirer for a paper that revealed the way commonly used statistical manipulations could lead to false results. As a test case he showed that by using acceptable practices, he could construct a statistically significant argument for the absurd result that listening to Paul McCartney's "When I'm 64" makes people get younger. Read that story here.

Here's what Science says about the scandal:

Clever statistical sleuthing by an anonymous fraud hunter in the United States appears to have led to the downfall of a marketing researcher at Erasmus University Rotterdam in the Netherlands. Today, the university announced in a statement (Dutch) that Belgian-born social psychologist Dirk Smeesters, who specialized in consumer behavior, resigned effective 21 June after an investigative panel found problems in his studies and concluded it had "no confidence in [their] scientific integrity." The university has also asked for the retraction of two of Smeesters' papers, one published in the Journal of Personality and Social Psychology in January and the other in the Journal of Experimental Social Psychology last year.

… Smeesters conceded to employing the so-called "blue-dot technique," in which subjects who have apparently not read study instructions carefully are identified and excluded from analysis if it helps bolster the outcome. According to the report, Smeesters said this type of massaging was nothing out of the ordinary. He "repeatedly indicates that the culture in his field and his department is such that he does not feel personally responsible, and is convinced that in the area of marketing and (to a lesser extent) social psychology, many consciously leave out data to reach significance without saying so."
Read more here.

And here's the latest on Simonsohn:
Erasmus University Rotterdam in the Netherlands has identified Uri Simonsohn, an associate professor at the Wharton School of the University of Pennsylvania, as the whistleblower in the case of psychologist Dirk Smeesters. The university today released the unredacted report from the investigative committee that looked into allegations of misconduct against Smeesters. The report describes how Simonsohn discovered statistical problems in a paper published last year in the Journal of Experimental Social Psychology by Smeesters and co-author Jia Liu of the University of Groningen in the Netherlands. (Erasmus University has said there is no reason to doubt the integrity of Smeesters's co-authors.) read more here.

And a post from retractionwatch here.

And an interesting Wired.com blog post on the fallout for Smeester's co-authors here.