2 Comments

GIGO. John Ioannidis is another who has pointed out that much published research is untrue and/or unreproducible.

I seem to remember that Malcolm Kendrick is very critical of meta-analysis. Yet I see frequent references online that they are a "gold standard" second only to RCT. It seems to be a useful way to add another obfuscating layer of statistical manipulation. Not to mention relatively inexpensive — no test tubes or live subjects needed, just a computer.

Hans Jürgen Eyseneck 25 years ago: ‘If a medical treatment has an effect so recondite and obscure as to require meta-analysis to establish it, I would not be happy to have it used on me’. https://academic.oup.com/eurheartj/article/40/40/3290/5594072

Expand full comment
author

"It seems to be a useful way to add another obfuscating layer of statistical manipulation."

Exactly. So convenient.

Great quote!

Expand full comment