Autori: Benassi, Mariagrazia , Bolzani, Roberto , Casadio, Roberta
Titolo: Validità statistica dei risultati in esperimenti a bassa numerosità campionaria. Simulazione di un test parametrico
Periodico: Giornale italiano di psicologia
Anno: 2013 - Fascicolo: 2 - Pagina iniziale: 353 - Pagina finale: 366

Many authors have criticized small sample size experiments because of thelack of statistical reliability, on the basis of the statistical power and considering a subjectiveevaluation of prior probability of the Null Hypothesis H0 (Cohen, 1994; Chertow,Palevsky e Green, 2006). The aim of the present study is to test the reliabilityof significant results obtained from the small sample size experiments in comparisonwith larger ones. The different samples (10, 20, 40, 80, 160) are obtained by MonteCarlo simulation, representing two conditions: H0 true and H0 false. As parametric procedure,the linear regression analysis has been used. Thus, the frequency of the type Ierror and the false positive rate probability (FPRP) have been evaluated. The frequencyof the I type error is around 5%, independently on the sample size. Moreover, theFPRP values obtained in the small size samples are comparable to the values obtainedin the larger samples. In conclusion the significant results obtained in small size samplesare reliable and have statistical validity as well as those obtained in larger samples.This is true even from a Bayesian point of view when a non-informative a priori probabilityof H0 is taken.


Premi sulle icone a fianco dei nomi per visualizzare i libri scritti dall'autore

---

---

SICI: 0390-5349(2013)2<353:VSDRIE>2.0.ZU;2-I
Testo completo: http://www.mulino.it/download/article/10.1421/74560
Testo completo alternativo: http://www.mulino.it/doi/10.1421/74560

Esportazione dati in Refworks (solo per utenti abilitati)

Biblioteche ACNP che possiedono il periodico