A NOTE ON THE SIMPLE STRUCTURAL REGRESSION MODEL

R. B. ARELLANO-VALLE AND H. BOLFARINE

Departamento de Estatística, IME, Universidade de São Paulo,
Caixa Postal 20570, CEP 05389-970, São Paulo, SP, Brasil

(Received August 15, 1994; revised June 8, 1995)

Abstract.    In this paper we investigate some aspects like estimation and hypothesis testing in the simple structural regression model with measurement errors. Use is made of orthogonal parametrizations obtained in the literature. Emphasis is placed on some properties of the maximum likelihood estimators and also on the distribution of the likelihood ratio statistics.

Key words and phrases:    Bartlett correction factors, information matrix, likelihood ratio statistics, maximum likelihood estimator, orthogonal parametrization, structural normal model.

Source ( TeX , DVI , PS )