Over the past decade it has become clear that there is a “replication crisis” in science, in which many noted and apparently important studies fail to repeat their results and very probably never should have been published in the first place. The factors contributing to this problem include the pressure to “publish or perish” that leads researchers to cut corners; the file-drawer problem, where seemingly nonsignificant results go unreported; data dredging and p-hacking, in which researchers manipulate statistical techniques to produce data that support their hypotheses; Texas sharpshooting, in which one draws a bull’s-eye around a random cluster of data and calls it a pattern; and the publication bias of journals that prefer original research over replication studies. These are all soluble problems, with practical solutions outlined in such books as Stuart Ritchie’s “Science Fictions.”

Read More »