Influence Diagnostics for Elliptical Multivariate Linear Regression Models

Abstract

The main object of this paper is to consider maximum likelihood estimators for models used in detection of analytical bias. We consider the regression model proposed in Ripley and Thompson (Analyst, 112, 1987, p. 377) with an EM-type algorithm for computing maximum likelihood estimators and obtain consistent estimators for the asymptotic variance of the maximum likelihood estimators, which seems not to be available in the literature. Wald type statistics are proposed for testing hypothesis related to the bias of the analytical methods with the asymptotic chi-square distribution which guarantees correct asymptotic significance levels. The main conclusion is that proposed approaches in the literature underestimate the covariance matrix of the maximum likelihood estimators. Results of simulation studies and applications to real data sets are reported to illustrate comparisons with other approaches. This journal is

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].…”

Influence diagnostics in the tobit censored response model

“…This method has had a great impact in the literature of the topic in the last decades. Several authors have extended the technique of local influence to more general regression models; see, e.g., Escobar and Meeker (1992), Paula (1993), Lawrence (1998), Galea et al (1997Galea et al ( , 2000Galea et al ( , 2004, Ortega et al (2003), Díaz-García et al (2003), Leiva et al (2007), Barros et al (2008), and Paula et al (2009).…”

Heteroscedasticity and/or autocorrelation checks in longitudinal nonlinear models with elliptical and AR(1) errors

“…Diagnostics of multivariate elliptical models have been studied in many literature. For example, Galea et al [10] , Liu [16,17] and Díaz-García et al [8] derived influence diagnostic graphics in multivariate elliptical linear models. Savalli et al [20] investigated a score-type test for one-sided alternatives to assess the variance components in elliptical linear mixed models.…”