in psychology, there is, or at least has been, a tendency to accept things as true if a single study showed it, thus causing the replication crisis, duh.

this runs contrary to what other branches of science do, which is to wait until a bunch of studies have been carried out and peer-reviewed, and cumulate the data from these studies to produce meta-analyses:

> A meta-analysis is a statistical analysis that combines the results of multiple scientific studies. Meta-analysis can be performed when there are multiple scientific studies addressing the same question, with each individual study reporting measurements that are expected to have some degree of error. The aim then is to use approaches from statistics to derive a pooled estimate closest to the unknown common truth based on how this error is perceived.

you're basically trying to gather as much data from as many different studies as possible in order to reach a conclusion, instead of relying on a single study. ideally, scientific consensus should be based on such analyses.

most of the reporting on scientific study results in the media are from individual studies, not meta-analyses. they might have reached correct conclusions, but they might also be flawed.

thus, in branches of science where the studies are few and the sample sizes are small, there are going to be more wrong theories.

when it comes to branches of science, my feeling is that they rank roughly like this in terms of how hard (scientific) they actually are:

1. physics
2. medicine
3. psychiatry
4. psychology
5. social anthropology
6. sociology
7. gender studies

@thor
First should be Mathematics