Clinical trial design as a decision problem

A Bayesian Randomized Clinical Trial: A Decision Theoretic Sequential Design

We propose a Bayesian decision theoretic framework for randomization in clinical trials. The proposed approach reconciles the apparent contradiction between the practice of clinical trial design and implications of a traditional decision theoretic setup. Although it is universal practice to use randomization in clinical trial design, a standard decision theoretic setup does not justify randomiz...

Battleships as Decision Problem

We define the well-known puzzle of Battleships as a decision problem and prove it to be NPcomplete, by means of a parsimonious reduction. By applying Valiant and Vazirani’s (1986) result we immediately obtain that the variant of this problem, viz. promising that there is a unique solution, is NP-complete as well, under randomized reductions. As this finding is in sheer contrast with the general...

DECISION-CTO: A "negative" clinical trial? Really?

Geoengineering as a design problem

Understanding the climate impacts of solar geoengineering is essential for evaluating its benefits and risks. Most previous simulations have prescribed a particular strategy and evaluated its modeled effects. Here we turn this approach around by first choosing example climate objectives and then designing a strategy to meet those objectives in climate models. There are four essential criteria f...

Recommendation as a Stochastic Sequential Decision Problem

Recommender systems — systems that suggest to users in e-commerce sites items that might interest them — adopt a static view of the recommendation process and treat it as a prediction problem. In an earlier paper, we argued that it is more appropriate to view the problem of generating recommendations as a sequential decision problem and, consequently, that Markov decision processes (MDPs) provi...