Knowledge that Transforms

We collect 2,848 instrumental variable (IV) regressions from 391 papers published in top economics and finance journals and show that estimated IV coefficients are often much larger than their OLS counterparts, even when theory suggests they should be smaller. We derive meta-regression estimators that distinguish measurement error bias from omitted variable bias and simultaneity bias; applying our estimators to a set of 1,040 comparable regressions from 139 papers, we find that measurement error shrinks reported coefficients by about two to four times. Measurement error remains quantitatively important even after accounting for weak instruments, publication bias, instrument invalidity, and heterogeneous treatment effects. Our results suggest that measurement error is a severe, pervasive, and understated source of bias in economics and finance.

Prior studies on cryptocurrency momentum overlook liquidation risk and other real-world frictions and inadequately assess its profitability. We evaluate time-series and cross-sectional momentum addressing these issues. When portfolios are marked to market daily, many cross-sectional momentum portfolios are liquidated, and those with statistically significant mean returns often earn negative profits. The mean return is insufficient for testing profitability in the cryptocurrency market, where returns are heavily skewed and fat-tailed. Evidence of time-series momentum is strong, whereas evidence of cross-sectional momentum is almost nonexistent. Investor overconfidence and the disposition effect appear to be important drivers of cryptocurrencies’ price dynamics.