[OskarS]

To give some extra context: this is another study confirming the "replication crisis"[1] in psychology and social psychology (and other sciences as well, but these are the most prominent fields) where longstanding results that were thought to be rock-solid are falling like dominoes. Basically, the science backing, like, half of all TED talks and most episodes of Radiolab is crumbling before our eyes.

[1] https://en.wikipedia.org/wiki/Replication_crisis

[averagewall]

It seems like the least competent people to be designing and analysing psychology studies are psychology researchers. Statistics should be the number one skill required. The psychology part of these high-profile studies is usually trivial so that anyone with no psychology background could have thought of it, or at least easily understand it. I don't really see the need for a specialist psychology researcher to do this kind of work. Maybe we need a new field - "studies of interesting everyday phenomena" that's mostly about doing statistics right.

[edilastic]

The irony is that a lot of statistics has really been developed in psychology and allied disciplines without even realizing. Meta-analysis, for example, really developed into its modern form in psychology, as a way of examining psychotherapy effects (even though the basic idea was around beforehand). Deep learning models too also have their roots in psychological models. They're called neural networks, but the models are more psychological than neurobiological per se, and have connections to other models that are firmly in the realm of psychological models.

[opportune]

I think you're being down voted because this might sound overly elitist, but to an extent I agree. As someone who considers himself relatively knowledgeable of statistics (coming from ML background) I have a hard time taking a lot of social science research seriously, because quite frankly, I am often left frustrated at the lack of rigor of their methodologies. Sample sizes are often way too small, and even more frequently, unacceptably biased to draw significant scientific conclusions. You also have the publication-bias problem which means that studies may be accepted as "legitimate" due to p-value hacking or because enough people were studying the problem that someone was bound to get a "statistically significant results" even when there was none.