Q-LEARNING WITH CENSORED DATA

We develop methodology for a multistage-decision problem with flexible number of stages in which the rewards are survival times that are subject to censoring. We present a novel Q-learning algorithm that is adjusted for censored data and allows a flexible number of stages. We provide finite sample bounds on the generalization error of the policy learned by the algorithm, and show that when the optimal Q-function belongs to the approximation space, the expected survival time for policies obtained by the algorithm converges to that of the optimal policy. We simulate a multistage clinical trial with flexible number of stages and apply the proposed censored-Q-learning algorithm to find individualized treatment regimens. The methodology presented in this paper has implications in the design of personalized medicine trials in cancer and in other life-threatening diseases.     

An extended proportional hazards model for interval-censored data subject to instantaneous failures

Lifetime Data Analysis - The proportional hazards (PH) model is arguably one of the most popular models used to analyze time to event data arising from clinical trials and longitudinal studies. In...     

What's an Oscar worth?

This article examines the impact of an Academy Award nomination and award for best picture, best actor/actress, and best supporting actor/actress on a film's (i) market share of theaters, (ii) average revenue per screen, and (iii) its probability of survival. The model is estimated using weekly box-office data for a matched sample of nominated and non-nominated films. The results indicate substantial financial benefits for a nomination and award for best picture and best actor/actress. The structure of rewards is consistent with that found in two-stage, single-elimination tournaments.     

Is bounded-vision an adequate explanation of strategic decision-making failures

One important area in which Management Science should be involved must surely be in the prevention of corporate failure. In this paper we therefore use a scientific methodology to try to identify the major causes of such failure. Two widely differing systems are examined and a large number of hypotheses considered as explanations of failure. In each case the only hypothesis which we are unable to reject, is that prior to the failure the dominant decision-makers in the system were not prepared to accept facts which were plainly available and which, if acted upon, could have prevented disaster. This allows us to suggest some ways of helping to prevent failure. Nevertheless, we feel that research into the mechanisms generating this phenomenon, which we have called bounded-vision, is required before adequate technologies can be designed.     

Inverse regression estimation for censored data

An inverse regression methodology for assessing predictor performance in the censored data setup is developed along with inference procedures and a computational algorithm. The technique developed here allows for conditioning on the unobserved failure time along with a weighting mechanism that accounts for the censoring. The implementation is nonparametric and computationally fast. This provides an efficient methodological tool that can be used especially in cases where the usual modeling assumptions are not applicable to the data under consideration. It can also be a good diagnostic tool that can be used in the model selection process. We have provided theoretical justification of consistency and asymptotic normality of the methodology. Simulation studies and two data analyses are provided to illustrate the practical utility of the procedure.