In common language we tend to use better than only when at least one of. Game theory lecture notes pennsylvania state university. A formal philosophical introduction richard bradley london school of economics and political science march 9, 2014 abstract decision theory. It is fairly obvious what the criterion should be for the falsification of a descriptive decision theory. In economics, game theory, and decision theory, the expected utility hypothesisconcerning peoples preferences with regard to choices that have uncertain outcomes gambles. I first, we will assume that all probabilities are known. Part ii decision theory chaos umpire sits, and by decision more embroils the fray by which he reigns.
Berger states the same principle within the context of a decision rule. A nice surprise for savages fans is that maximizing expected utility is a safe way, and often, at least approx. I then, we will study the cases where the probabilistic structure is not. Identify the possible outcomes, called the states of nature or events for the decision problem. Kathryn blackmondlaskey spring 2020 unit 1 2you will learn a way of thinking about problems of inference and decision making under uncertainty you will learn to construct mathematical models for inference and decision problems you will learn how to apply these models to draw inferences from data and to make decisions these methods are based on bayesian decision theory, a formal. Economic theorists have been concerned with this problem since the days of jeremy bentham 17481832. Shuang liang, sse, tongji minimum risk classification the general decision rule ax tells us which action to take for observation x we want to find the decision rule that minimizes the overall risk. Bayesian decision theory is a fundamental statistical approach to the problem of pattern classification.
Minimax sometimes minmax, mm or saddle point is a decision rule used in artificial intelligence, decision theory, game theory, statistics, and philosophy for minimizing the possible loss for a worst case maximum loss scenario. Game theory, maximum entropy, minimum discrepancy and robust bayesian decision theory. The term is called the likelihood ratio, and the decision rule is known as the likelihood ratio test l can be disregarded in the decision rule since it is constant regardless of. Some characteristic problems in decision theory every day we have to make decisions. Fundamentals of decision theory university of washington. Decision theory steps involved in decision theory approach. When dealing with gains, it is referred to as maximinto maximize the minimum. Classical is a family of theories which, on the assumption that features of the world relevant to ones decisions are themselves unaffected by those decisions, aims to give an precise account of how to choose game theory see game theory is the calculus. Decision theory is about how to behave optimally under uncertainty. Decision theory deals with methods for determining the optimal course of action when a number of alternatives are available and their consequences cannot be forecast with certainty. Introduction bayesian decision theory minimum errorrate classifier and discriminant function three approaches cs559 machine.
Introduction to risk and uncertainty, decisions under uncertainty using laplace, maximin, minimax, maximax, minimin, hurwicz and savage methods some elements are common for all kinds of decisions the decision makerthe decision maker is refers to an individual or a group of individuals. Decision theory and bayesian methods summary when there is data decision space is the set of possible actions i might take. F1 a decision theory is falsified as a descriptive theory if a decision problem can be found in which most human subjects perform in contradiction to the theory. To sum up, this minimumexpectedloss idea gives us a straightforward.
Determine the various alternative courses of actions from which the final decision has to be made. He then chooses the alternative that yields the greatest of those minimum payoffs. Decision theory a calculus for decision making under uncertainty decision theory is a calculus for decision making under uncertainty. We assume that it is convex, typically by expanding a basic decision space d to the space d of all probability distributions on d. Game theory, maximum entropy, minimum discrepancy and robust bayesian decision theory1 by peter d. Bayesian decision theory pattern recognition, fall 2012 dr. Decision tree, information gain, gini index, gain ratio, pruning, minimum description length, c4. Game theory, maximum entropy, minimum discrepancy and. If theres time, well study evolutionary game theory, which is interesting in its own right.
Chapter 5 bayes methods and elementary decision theory. Philip dawid cwi amsterdam and university college london we describe and develop a close relationship between two problems that have customarily been regarded as distinct. Decision making under uncertainty mit opencourseware. In recent years the development of the economic theory of consumers decision making or, as the 1 thi s work wa supported by contract. An overview of decision theory international nuclear.
Resnick, choices an introduction to decision theory. According to utilitarian moral theory, all moral decisions should, at least in principle, consist of attempts to maximize the total amount of utility. An interdisciplinary approach to determine how decisions are made given unknown variables and an uncertain decision environment framework. In the leasing example, the minimax decision maker notes that the percentof. We may also investigate combinatorial game theory, which is interested in games like chess or go. We wish to make a decision on a signal of interest using noisy measurements. Its a little bit like the view we took of probability. For each value of x, we have a different class conditional pdf for each class in w example next slide. The minimum of these column maximums is 6, the decision is a 1.
Decision theory chris williams school of informatics, university of edinburgh october 2010 115 overview classication and bayes decision rule sampling vs diagnostic paradigm classication with gaussians loss, utility and risk reject option reading. It is considered the ideal case in which the probability structure underlying the categories is known perfectly. Fundamentals of decision theory decision theory steps in. Quanti es the tradeo s between various classi cations using probability and the costs that accompany such classi cations. The bayesian approach, the main theme of this chapter, is a particular way of formulating and dealing.
This gives you the minimimax estimator which is 2 here. Bayesian decision theory is a fundamental statistical approach to the problem of pattern classi cation. Decision theory as the name would imply is concerned with the process of making decisions. Warnernorth abstract decision theory provides a rational framework for choosing between alternative courses of action when the conse quences resulting from this choice are imperfectly known.
We here generalize this theory to apply to arbitrary decision problems and loss functions. John miller and aran nayebi in this lecture1, we will introduce some of the basic concepts of statistical decision theory, which will play crucial roles throughout the course. Decision theory deals with methods for determining the optimal course of. Components of x are binary or integer valued, x can take only one of m discrete values v. Roughly, a theory is ascriptive if it is robust to its own publication. F3 a decision theory is strict ly falsified as a norma tive theory if a decision problem can be f ound in which an agent w ho performs in accordance with the theory cannot be a rational ag ent. Basic concepts of statistical decision theory lecturer. A formal philosophical introduction richard bradley london school of economics and political science march 9, 2014 abstract decision theory is the study of how choices are and should be. If the likelihood ratio of class 1 and class 2 exceeds a threshold value independent of the input pattern x, the optimal action is.
The elements of decision theory are quite logical and even perhaps intuitive. Statistical decision theory bayes inference statistical decision theory statistical decision theory is concerned with the problem of making decisions. Bayesian decision theory an overview sciencedirect topics. Bayesian decision theory discrete features discrete featuresdiscrete features. The economic theory of decision making is a theory about how to predict such decisions. The decision tree consists of nodes that form a rooted tree. The extension to statistical decision theory includes decision making in the presence of statistical knowledge which provides some information where there is uncertainty. Conversely, walds maximin criterion 75 takes into account the least. The minimax regret criterion advices you to choose the option with the lowest.
1496 1283 97 989 47 748 1166 637 450 1131 246 1367 914 88 64 1008 1156 296 761 1038 785 783 863 315 776 46 1166 161 3 1469 372 721 1187