domains / families / research / 07-phack-immunization

07-phack-immunization

separate

Make an empirical analysis robust to specification search, before or after the fact. Covers pre-registration and pre-analysis plans encoded as design cards, specification-curve reporting with the Simonsohn joint tests, Romano-Wolf and effective-multiplicity corrections, full-procedure null calibration including for sequential searches, the distance-from-pre-registration diagnostic, split-sample and holdout designs, and the auto-generated honest report. Use when asked how to protect an analysis against p-hacking, how to correct inference after a search has happened, how to write a pre-analysis plan, or how to report a multiverse credibly.

When to use

• protecting analysis against p-hacking
• correcting inference after a search
• writing a pre-analysis plan
• reporting a multiverse credibly
• pre-registration and pre-analysis plans
• specification-curve reporting
• Romano-Wolf and effective-multiplicity corrections
• full-procedure null calibration

Skill page

Source