Autore
De Martini, Daniele

Titolo
Reproducibility probability estimation for testing statistical hypotheses.
Periodico
Università degli Studi del Piemonte Orientale 'A. Avogadro' : Facoltà di Economia - Dipartimento di Scienze Economiche e Metodi Quantitativi "SEMEQ" - Quaderni
Anno: 2006 - Volume: 06 - Fascicolo: 16 - Pagina iniziale: 1 - Pagina finale: 10

The application of statistical tests often generates problems, because of their randomncss. Here, stemming from the variability of statistical tests, the reproducibility probability of a statistically significative result (RP) is estimated first. Then, statistical tests are defined on the basis of RP estimation. Lower bounds for RP, and then pointwise RP estimates are used. It is emphasized that the threshold for the RP pointwise estimator to define statistical tests turns out to be 1/2. Hence, taking the perspective of RP estimation, one can compute statistical tests and have suitable interpretations of their results. Keywords: Noncentrality parameter estimation; plug-in power estimation; statistical tests definitions.




Esportazione dati in Refworks (solo per utenti abilitati)