Nonparametric Predictive Inference (NPI) is a general methodology to learn from data in the absense of prior knowledge and without adding unjustified assumptions. This paper develops NPI for multinominal data where the total number of possible categories for the data is known. We present the...

Game-theoretic solution concepts such as Nash and Bayesian equilibrium start from an assumption that the players’ sets of possible payoffs, measured in units of von Neumann–Morgenstern utility, are common knowledge, and they go on to define rational behavior in terms of equilibrium strategy...

This paper constructs a robust optimization framework of the uncertain worst-case return. The model defines an adjustable discrete uncertainty set which controls the conservatism of the optimal asset allocation. Without prior assumptions on the data generating process, the model also develops an...

Portfolio optimization results are strongly dependent on the model parameters. To circumvent this shortcoming, this paper proposes a new modeling approach to address data uncertainty. The model offers full control over the degree of conservatism and underlines its interaction with robustness for...

Measuring the accuracy of diagnostic tests is crucial in many application areas, in particular medicine and health care. The receiver operating characteristic (ROC) surface is a useful tool to assess the ability of a diagnostic test to discriminate among three ordered classes or groups....