On asymptotic normality of parameters in multiple linear errors-in-variables model (Q1433517)

Errors-in-variable models are regression models with errors in both the dependent and the independent variables. Consistent estimation of the parameters in the regression function requires the imposition of certain restrictive conditions on the error variances. Here multi-dimensional linear models of this kind are studied, with replicated observations being available at some experimental points. This allows the establishing of asymptotic normality under mild constraints and the estimation of the parameters in the asymptotic variance.