Search Results
Showing results 1 to 4 of approximately 4.
(refine search)
Report
Star Wars at Central Banks
We investigate the credibility of central bank research by searching for traces of researcher bias, which is a tendency to use undisclosed analytical procedures that raise measured levels of statistical significance (stars) in artificial ways. To conduct our search, we compile a new dataset and borrow 2 bias-detection methods from the literature: the p-curve and z-curve. The results are mixed. The p-curve shows no traces of researcher bias but has a high propensity to produce false negatives. The z-curve shows some traces of researcher bias but requires strong assumptions. We examine those ...
Report
Online Appendix for: Comment on "Star Wars: The Empirics Strike Back"
This appendix contains the pre-registered analysis for our comment on “Star Wars: The Empirics Strike Back” by Brodeur et al (2016). To structure the analysis, we reproduce the pre-registration; our results appear in red under each of the relevant parts. The time-stamped version of the pre-registration is available from the Open Science Framework website at the address https://doi.org/10.17605/OSF.IO/58MNJ.To understand this appendix deeply, we recommend carefully reading Brodeur et al (2016). The body of our comment paper outlines only the intuition of their method. In some of the ...
Report
Comment on "Star Wars: The Empirics Strike Back"
Using a novel meta-analytical method, Brodeur et al. (2016) argue that hypothesis tests in top economic journals have exaggerated levels of statistical significance. Brodeur et al. (2020) apply the same method to another sample of hypothesis tests, obtaining similar results. We investigate the reliability of the method by highlighting questionable assumptions and compiling a dataset to examine their merits. Our findings support the original conclusions.