In this note we consider the D-optimal design problem for the heteroscedastic polynomial regression model. Karlin and Studden (1966a) found explicit solutions for three types of efficiency functions. We introduce two ‘new’ functions to model the heteroscedastic structure, for which the...

We show that previous results on the asymptotic efficiency of OLS versus GLS in the context of trending data carry over to regressors of the fractionally integrated type.

We describe a computer intensive method for linear dimension reduction which minimizes the classification error directly. Simulated annealing Bohachevsky et al (1986) is used to solve this problem. The classification error is determined by an exact integration. We avoid distance or scatter...

In this paper we examine two widely used methods to obtain a transformation in Taguchi experiments, namely the lambda plot and the beta technique. We consider different situations with contrasts influencing the mean and / or the variance of the response. Our simulation study reveals that the...

The correlated Weibull regression model for the analysis of correlated binary data is presented. This regression model is based on Bonney’s disposition model for the regression analysis of correlated binary outcomes. Parameter estimation was done through the maximum likelihood method. The...

This note shows that the Augmented Dickey-Fuller test is consistent against fractional alternatives if the order of the autoregression does not tend to infinity too fast.

This paper analyzes linear models. It investigates the difference between the sum of squares of the residuals and the sum of squares of the prediction errors when the parameter is estimated consecutively. In case the regressors are “fractionally integrated” (in a very broad sense) it is...

We consider empirical autocorrelations of residuals from infinite variance autoregressive processes. Unlike the finite-variance case, it emerges that the limiting distribution, after suitable normalization, is not always more concentrated around zero when residuals rather than true innovations...