Reusing Natural Experiments

Finance & Accounting

Speaker:Matthew C. Ringgenberg , University of Utah
Date: Wednesday 4 November 2020
Time: 16:00 - 17:00
Location: Zoom

Further details

After a natural experiment is fi rst used, other researchers often reuse the setting, examining
di erent outcome variables. We examine the consequences of reusing an experimental
setting using two extensively studied natural experiments, business combination laws and
the Regulation SHO pilot. We apply multiple hypothesis corrections and our ndings
suggest many results in the existing literature are false positives. We provide guidelines
for inference when an experiment is reused using simulation evidence for several popular
empirical settings including di erence-in-di erences regressions, instrumental variables
regressions, and regression discontinuity designs.