Local Influence in Comparative Calibration Models Under Ellipticalt -Distributions

Abstract

In this paper we consider applications of local influence (Cook, 1986) to evaluate small perturbations in the model or data set in the context of structural comparative calibration (Bolfarine and Galea, 1995) assuming that the measurements obtained follow a multivariate elliptical distribution. Different perturbation schemes are investigated and an application is considered to a real data set, using the elliptical t-distribution.

Influence diagnostics in Gaussian spatial linear models

“…Further results on local influence and applications in linear regression and mixed models can be found in [1,12,15,17,18,[25][26][27].…”

An extension of Birnbaum-Saunders distributions based on scale mixtures of skew-normal distributions with applications to regression models

“…This diagnostic technique has been studied by many authors, for example, Thomas and Cook (1990), who presented a study of local influence in generalized linear model, Lesaffre and Verbeke (1998)), who considered the local influence in the mixed linear model, Zhao and Lee (1998), who applied the local influence method in the model of simultaneous equations, and Galea et al (1997), who applied the method in the elliptical linear regression model. Galea et al (2005) present a diagnostic study in the comparative calibration model, considering that the data follow a Student-t distribution.…”