We investigate the asymptotic behavior of the WALS estimator, a model-averaging estimator with attractive finite-sample and computational properties. WALS is closely related to the normal location model, and hence much of the paper concerns the asymptotic behavior of the estimator of the unknown...

This papers offers a theoretical explanation for the stylized fact that forecast combinations with estimated optimal weights often perform poorly in applications. The properties of the forecast combination are typically derived under the assumption that the weights are fixed, while in practice...

This article presents a study of the (conditional) probability of winning a point on service, based on almost 90,000 points played at Wimbledon, 1992-1995. We show that points are neither independent nor identically distributed, and we present an extended logit model that captures the dependence...

We consider the question whether top tennis players in a top tournament (Wimbledon) employ an optimal (efficient) service strategy. We show that top players do not, in general, follow an optimal strategy, and we provide a lower bound of the inefficiency. The inefficiency regarding winning a...

In specifying a regression equation, we need to determine which regressors to include, but also how these regressors are measured. This gives rise to two levels of uncertainty: concepts (level 1) and measurements within each concept (level 2). In this paper we propose a hierarchical weighted...

This papers offers a theoretical explanation for the stylized fact that forecast combinations with estimated optimal weights often perform poorly in applications. The properties of the forecast combination are typically derived under the assumption that the weights are fixed, while in practice...