Hypothesis-Testing Demands Trustworthy Data—A Simulation Approach to Inferential Statistics Advocating the Research Program Strategy
| Autor: | Frank Zenker, Erich H. Witte, Antonia Krefeld-Schwalb |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
replication
Wald criterion Bayesian probability lcsh:BF1-990 likelihood Likelihood Replication 050109 social psychology Inferential statistics Machine learning computer.software_genre Bayesian inference 050105 experimental psychology Statistical power Wald Bayes' theorem Frequentist inference ddc:650 Feature (machine learning) Statistical inference Methods Psychology 0501 psychology and cognitive sciences General Psychology Statistical hypothesis testing Criterion business.industry 05 social sciences inferential statistics T-test t-test research program strategy Research program strategy lcsh:Psychology Artificial intelligence business computer |
| Zdroj: | Frontiers in Psychology Frontiers in Psychology, Vol 9 (2018) Frontiers in Psychology, Vol. 9 (2018) P. 14 |
| ISSN: | 1664-1078 |
| Popis: | In psychology as elsewhere, the main statistical inference strategy to establish empirical effects is null-hypothesis significance testing (NHST). The recent failure to replicate allegedly well-established NHST-results, however, implies that such results lack sufficient statistical power, and thus feature unacceptably high error-rates. Using data-simulation to estimate the error-rates of NHST-results, we advocate the research program strategy (RPS) as a superior methodology. RPS integrates Frequentist with Bayesian inference elements, and leads from a preliminary discovery against a (random) H0-hypothesis to a statistical H1-verification. Not only do RPS-results feature significantly lower error-rates than NHST-results, RPS also addresses key-deficits of a "pure" Frequentist and a standard Bayesian approach. In particular, RPS aggregates underpowered results safely. RPS therefore provides a tool to regain the trust the discipline had lost during the ongoing replicability-crisis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|