« Map of Springfield | Main | Galton was a hero to most »

October 22, 2006

Torture the data until it admits to everything

From the long New York Times article on an example of scientific fraud by grant-hogging entrepreneurs-in-academia, imputation was used as an excuse for manipulating data to support the anticipated hypothesis:

Then, when pressed on how fictitious numbers found their way into the spreadsheet he’d given DeNino, Poehlman laid out his most elaborate explanation yet. He had imputed data β€” that is, he had derived predicted values for measurements using a complicated statistical model. His intention, he said, was to look at hypothetical outcomes that he would later compare to the actual results. He insisted that he never meant for DeNino to analyze the imputed values and had given him the spreadsheet by mistake. Although data can be imputed legitimately in some disciplines, it is generally frowned upon in clinical research, and this explanation came across as hollow and suspicious, especially since Poehlman appeared to have no idea how imputation was done.

The sentence was one year and one day in federal prison, followed by two years of probation.

Posted by Aleks at October 22, 2006 8:56 PM

RSS feed for this entry.

Trackback Pings

TrackBack URL for this entry:
http://www.stat.columbia.edu/~cook/movabletype/mt-tb.cgi/661

Comments

A year in prison for imputation, huh? Very funny. It's a good thing he didn't do multiple imputation, maybe then he would've been given several sentences. On the other hand, maybe they could served in parallel...

Actually, just to be fair, if you read the article carefully, it said that Poehlman did not actually use imputation: this was just one of the flimsy excuses he tried out before giving up entirely.

Perhaps the more interesting question is why there isn't more fraud. Every time a case like this comes up, it somehow seems like such a surprise, but with a million scientists out there, some of them have to be bad guys, right?

Posted by: Andrew [TypeKey Profile Page] at October 23, 2006 7:18 AM.

Post a comment




Remember Me?

(you may use HTML tags for style)