No. 266 · Evidence · Heuristics and Bias
Publication Bias
The studies we read are often the lucky survivors of all the studies that were run.
In the Almanac
“The file drawer”, 1959–1979 · “GlaxoSmithKline and Paxil”, 2001–2015
Both stories in full, three ways to use it and where it misleads.
Get the AlmanacQuestions
What is Publication Bias?
Publication Bias is the tendency for exciting, positive findings to be published while negative or inconclusive studies stay in the file drawer. Over time, the visible evidence looks far stronger than reality.
How do you avoid Publication Bias?
When a result seems too clean or too exciting, ask how many studies found nothing. Prefer pooled reviews and registered trials over single headlines. Apply the same thinking to success stories and social media: you are seeing the published wins, not the hidden misses.
When does Publication Bias matter?
Publication Bias is one of the 68 mental models for evidence, the situations where you ask: Is this really true? Within that, it belongs to “When research goes wrong”, alongside Anecdotal Evidence, Data Dredging and Hasty Generalisation.
What is an example of Publication Bias?
Two stories show it at work: The file drawer (1959–1979) and GlaxoSmithKline and Paxil (2001–2015). Both are told in full in The Mental Models Daily Almanac, which has two stories for each of its 365 models.
Which mental models are related to Publication Bias?
Survivorship Bias, Systematic Review and Bias from Incentives. Publication Bias itself comes from heuristics and bias.