Modelli lineari ad intercetta casuale, stimatori e valutazione di sistemi formativi

Abstract

This paper presents two intercept estimators, an ordinary one and an empirical Bayesian one, for a multilevel linear regression model where the intercept is treated as a random variable. These estimators can be used as effectiveness indicators for the evulation of the classes, which may vary in terms of the students' characteristics as well as the problems in the student/teacher relationship. The differences between classes size and the intraclass correlation coefficient value, show that empirical Bayes estimator is more efficient than the ordinary estimator.