Piling on, here is Alone on diet studies:

"A glance at the methodology has more practical value than the little asterisk above a score at month 6." - regarding the uselessness and distraction of p-values.

"the purpose of these studies is not to determine the answer, the purpose of these studies is to be published"

That's actually a recurring theme in his posts. In this one he analyses the methodology of a study on a Bipolar Disorder drug. Conclusion - the authors claim the study shows that the drug is 50% more effective than a placebo. What the study actually shows, when one looks at the methodology, is that among people who responded well to the drug, 50% of them suffered relapse when the drug was discontinued. This is not surprising. And it doesn't say what the actual efficacy of the drug is at all.