False Discovery Rate: applicazione di un metodo alternativo per i confronti multipli con misure ripetute
Are you already subscribed?
Login to check
whether this content is already included on your personal or institutional subscription.
Abstract
The present paper is aimed at presenting an application to reaction times of an alternative data analysis method for treating unplanned comparisons in a repeated measures series. We compared such method with two different procedures. The first procedure consisted of a series of single pairwise comparisons, without controlling for type I error. The second procedure was the standard version of the Bonferroni method. It is worth noting that, as the number of comparisons gets larger, with the first method a substantial increase of the probability to make a Type I error is observed. Conversely, with the application of the method developed by Bonferroni, the increase in the number of comparisons results in a higher probability of making a Type II error. The empirical comparison, supported by a "Bootstrap" analysis, allowed to show that the alternative method, known as "False Discovery Rate" (FDR) possesses many advantages and is particularly easy to implement.