Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
How robust are experimental results to changes in design? And can researchers anticipate which changes matter most? We consider a real-effort task with multiple behavioral treatments and examine the stability along six dimensions: (i) pure replication, (ii) demographics, (iii) geography and culture, (iv) the task, (v) the output measure, and (vi) the presence of a consent form. We find near-perfect replication of the experimental results and full stability of the results across demographics, significantly higher than a group of experts expected. The results differ instead across task and output change, mostly because the task change adds noise to the findings.