A precise null hypothesis formulation (instead of the more realistic interval one) is usually adopted in statistical packages although it generally leads to excessive (and often misleading) rates of rejection whenever the sample size is large. In a previous paper (Migliorati and Ongaro 2007) we proposed a calibration procedure aimed at adjusting test levels and p-values when testing the mean of a Normal model with known variance. We address now the more complicated calibration issues arising when a nuisance parameter (e.g. the variance) is present. This entails, in particular, the construction of suitable tests for the interval null hypothesis
Migliorati, S., Ongaro, A. (2010). Adjusting p-values when n is large in the presence of nuisance parameters. In C.H. Skiadas (a cura di), Advances in data analysis (pp. 305-318). Boston : Birkhauser [10.1007/978-0-8176-4799-5_25].
Adjusting p-values when n is large in the presence of nuisance parameters
MIGLIORATI, SONIA;ONGARO, ANDREA
2010
Abstract
A precise null hypothesis formulation (instead of the more realistic interval one) is usually adopted in statistical packages although it generally leads to excessive (and often misleading) rates of rejection whenever the sample size is large. In a previous paper (Migliorati and Ongaro 2007) we proposed a calibration procedure aimed at adjusting test levels and p-values when testing the mean of a Normal model with known variance. We address now the more complicated calibration issues arising when a nuisance parameter (e.g. the variance) is present. This entails, in particular, the construction of suitable tests for the interval null hypothesis
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
