significant and theory-confirming estimates for publication. Meta-regression models were originally developed for the synthesis of … statistically significant and theory-confirming estimates. Each regression specification may possibly suffer from biases such as … authors of primary studies search for statistically significant and theory-confirming estimates, meta-regression models tend …

-hacking or publication bias, in particular for articles using DID or IV as causal identification method. We show that a crucial … then find no evidence for p-hacking or publication bias in the DID and pooled data, but evidence remains for IV …