Scientists use apolitical methods of testing their hypothesesMike Rappaport

So says Judge Posner, in a post that I criticize.  Yet, we know there are serious biases involved in such studies. See this post.  Here is an excerpt:

In 1995, the Journal of American Medical Association reported that of 250 studies of treatments, those with easier fudging similarly “found” stronger effects:

Comparedwith trials in which authors reported adequately concealed treatmentallocation, … Odds ratios were exaggerated by 41% for inadequatelyconcealed trials and by 30% for unclearly concealed trials … Trialsthat were not double-blind also yielded … odds ratios beingexaggerated by 17%

See also this comment.