Data replication matters to an underpowered study, but replicated hypothesis corroboration counts

Erich H. Witte, Frank Zenker

Research output: Contribution to journalDebate/Note/Editorialpeer-review

2 Citations (SciVal)


Before replication becomes mainstream, the potential for generating theoretical knowledge better be clear. Replicating statistically significant nonrandom data shows that an original study made a discovery; replicating a specified theoretical effect shows that an original study corroborated a theory. Yet only in the latter case is replication a necessary, sound, and worthwhile strategy.

Original languageEnglish
Pages (from-to)e156
JournalBehavioral and Brain Sciences
Publication statusPublished - 2018

Subject classification (UKÄ)

  • Philosophy

Cite this