Paper
1994
The Earth Is Round (p < .05)
Jacob Cohen
Argues null-hypothesis significance testing does not tell researchers what they think it does - it cannot say how probable a hypothesis is - and that psychology's near-total reliance on it has done the field lasting damage.
Read itBefore you start
FreeEntry
Read these first
Not a difficulty warning — a route. These are in the library too.
If this is the wrong level
Groundwork for
Works in the library that name this one as a prerequisite.
- The New Statistics: Why and HowGeoff Cumming, 2014Argues psychology should replace single-study null-hypothesis significance testing with estimation, confidence intervals and cumulative meta-analysis across studies, because a single p-value cannot say how big an effect is or how much to trust it.
- Why Most Discovered True Associations Are InflatedJohn P. A. Ioannidis, 2008Argues that even a genuinely true effect, once it clears a significance threshold in an underpowered or heavily tested literature, will on average have its estimated size inflated by the same selection process that produces false positives.
Filed under Research Methods & the Replication Crisis in Psychology.