Goodness-of-fit tests in mixed models Academic Article

abstract

• Mixed models, with both random and fixed effects, are most often estimated on the assumption that the random effects are normally distributed. In this paper we propose several formal tests of the hypothesis that the random effects and/or errors are normally distributed. Most of the proposed methods can be extended to generalized linear models where tests for non-normal distributions are of interest. Our tests are nonparametric in the sense that they are designed to detect virtually any alternative to normality. In case of rejection of the null hypothesis, the nonparametric estimation method that is used to construct a test provides an estimator of the alternative distribution. 2009 Sociedad de Estadstica e Investigacin Operativa.

authors

• Hart, Jeffrey

published proceedings

• TEST

author list (cited authors)

• Claeskens, G., & Hart, J. D.

citation count

• 31

complete list of authors

• Claeskens, Gerda||Hart, Jeffrey D

publication date

• August 2009

publisher

• Springer Nature  Publisher

published in

• Test  Journal

keywords

• Hypothesis Test
• Minimum Distance
• Mixed Model
• Nonparametric Test
• Order Selection

Digital Object Identifier (DOI)

• 10.1007/s11749-009-0148-8

start page

• 213

end page

• 239

volume

• 18

issue

• 2

URL

• http%3A%2F%2Fdx.doi.org%2F10.1007%2Fs11749-009-0148-8