Group items tagged

"As we get more data, we can fit more model. But at some point we become so overwhelmed by data that, for computational reasons, we can barely do anything at all. Thus, the curve above could be thought of as the product of two curves: a steadily increasing curve showing the statistical ability to fit more complex models with more data, and a steadily decreasing curve showing the computational feasibility of doing so."

"Someone points me to this report from Tilburg University on disgraced psychology researcher Diederik Stapel. The reports includes bits like this: When the fraud was first discovered, limiting the harm it caused for the victims was a matter of urgency. This was particularly the case for Mr Stapel's former PhD students and postdoctoral researchers . . . However, the Committees were of the opinion that the main bulk of the work had not yet even started. . . . Journal publications can often leave traces that reach far into and even beyond scientific disciplines. The self-cleansing character of science calls for fraudulent publications to be withdrawn and no longer to proliferate within the literature. In addition, based on their initial impressions, the Committees believed that there were other serious issues within Mr Stapel's publications . . . This brought into the spotlight a research culture in which this sloppy science, alongside out-and-out fraud, was able to remain undetected for so long. . . . The scientific literature must be cleansed of everything that is fraudulent, especially if it involves the work of a leading academic. Sounds familiar? I think it also applies to recipients of the Founders Award from the American Statistical Association. There's more: The most important reason for seeking completeness in cleansing the scientific record is that science itself has a particular claim to the finding of truth. This is a cumulative process, characterized in empirical science, and especially in psychology, as an empirical cycle, a continuous process of alternating between the development of theories and empirical testing. . . . My first reaction was that all seems like overkill given how obvious the fraud is, but given what happened with comparable cases in the U.S., I suppose this "Powell doctrine" approach (overwhelming force) is probably the best way to go."

After reading your recent post, I thought you might find this interesting - especially the scanned interview that is included at the bottom of the posting. It's an old OMNI interview with Walter Stewart that was the first thing I read (at a young and impressionable age ;) about the prevalence of errors, fraud and cheating in science, the institutional barriers to tackling it, the often high personal costs to whistleblowers, the difficulty of accessing scientific data to repeat published analyses, and the surprisingly negative attitude towards criticism within scientific communities. Highly recommended entertaining reading - with some good examples of scientific investigations into implausible effects. The post itself contains the info I once dug up about what happened to him later - he seems like an interesting and very determined guy: when the NIH tried to stop him from investigating scientific errors and fraud he went on a hunger strike.