"Specifically, Popper makes clear that (1) scientists should replicate their own experiments; (2) scientists should be able to instruct other experts how to reproduce their experiments and get the same results; and (3) establishing the reproducibility of experiments (“direct replication” in the parlance of our times) is a necessary precursor for all the other things you do to construct and test theories."
New blog post: An open review of Many Labs 3. The upshot: Not much replicated (perhaps less than it appears). No interactions replicated, almost certainly due to power issues. One original study missed its hypothesized effect, also probably due to power. Emblematic problems with a "conceptual replication." And another blow to the hidden moderator defense.
Statistics as math vs. statistics as tools. My new blog post about how different frames might affect how statisticians and scientists communicate and miscommunicate, and some ideas of what to do about it.