Project SherlockEst. Knowledge

Paper

2012

An Agenda for Purely Confirmatory Research

Eric-Jan Wagenmakers, Ruud Wetzels, Denny Borsboom, Han L. J. van der Maas & Rogier A. Kievit

Argues psychology has collapsed the distinction between generating a hypothesis from data and confirming it with new data, and that separating the two by preregistering every confirmatory analysis before collecting data is the fix.

Before you start

FreeIntermediate

Read these first

Not a difficulty warning — a route. These are in the library too.

Feeling the Future: Experimental Evidence for Anomalous Retroactive Influences on Cognition and AffectDaryl J. Bem, 2011Reports nine experiments finding that ordinary participants' current behaviour was statistically influenced by random events that had not yet happened, using entirely standard psychological methods - a result now widely read not as evidence for precognition but as proof that those standard methods could manufacture significant findings for almost anything.

Groundwork for

Works in the library that name this one as a prerequisite.

Registered Reports: A New Publishing Initiative at CortexChristopher D. Chambers, 2013Announces a journal format in which the introduction and methods are peer reviewed and provisionally accepted before the results are known, arguing this removes the incentive to change a study's story to fit whatever result comes out.

Filed under Research Methods & the Replication Crisis in Psychology.