In statistics, samples are drawn from a population in a datagenerating process (DGP). Standard errors measure the uncertainty in sample estimates of population parameters. In science, evidence is generated to test hypotheses in an evidencegenerating process (EGP). We claim that EGP variation across researchers adds uncertainty: non-standard errors. To study them, we let 164 teams test six hypotheses on the same sample. We find that non-standard errors are sizeable, on par with standard errors. Their size (i) co-varies only weakly with team merits, reproducibility, or peer rating, (ii) declines significantly after peer-feedback, and (iii) is underestimated by participants.

This paper analyzes the effects of bank capital regulation on the link between bank size and volatility. Using bank-level data for 27 advanced economies over the 2000–2014 period, we estimate a power law that relates the volume of a bank’s loan portfolio to the volatility of loan growth. Our analysis reveals, first, that more stringent capital regulation weakens the size-volatility nexus. Hence, in countries with more stringent capital regulation, large banks show, ceteris paribus, lower loan portfolio volatility. Second, the effect of tighter capital requirements on the size-volatility nexus becomes stronger for the upper tail of the bank size distribution. This is in line with capitalization decreasing with bank size, such that larger banks tend to be more affected by increasing capital requirements. Third, in countries with higher sectoral capital buffers, the size-volatility nexus is weaker.