Sample Selection

[This Guest Blog is a repost of a blog by Markus Eberhardt, published at Vox – CEPR Policy Portal] Recent evidence suggests that a country switching to democracy achieves about 20% higher per capita GDP over subsequent decades. This column demonstrates the sensitivity of these findings to sample selection and presents an implementation which generalises the empirical approach.

Replication researchers cite inflated effect sizes as a major cause of replication failure. It turns out this is an inevitable consequence of significance testing. The reason is simple. The p-value you get from a study depends on the observed effect size, with more extreme observed effect sizes giving better p-values; the true effect size plays no role.