This paper presents a critique of expected utility theory as a descriptive model of decision making under risk, and develops an alternative model, called prospect theory. Choices among risky prospects exhibit several pervasive effects that are inconsistent with the basic tenets of utility theory. In particular, people underweight outcomes that are merely probable in comparison with outcomes that are obtained with certainty. This tendency, called the certainty effect, contributes to risk aversion in choices involving sure gains and to risk seeking in choices involving sure losses. In addition, people generally discard components that are shared by all prospects under consideration. This tendency, called the isolation effect, leads to inconsistent preferences when the same choice is presented in different forms. An alternative theory of choice is developed, in which value is assigned to gains and losses rather than to final assets and in which probabilities are replaced by decision weights. The value function is normally concave for gains, commonly convex for losses, and is generally steeper for losses than for gains. Decision weights are generally lower than the corresponding probabilities, except in the range of low prob- abilities. Overweighting of low probabilities may contribute to the attractiveness of both insurance and gambling. EXPECTED UTILITY THEORY has dominated the analysis of decision making under risk. It has been generally accepted as a normative model of rational choice (24), and widely applied as a descriptive model of economic behavior, e.g. (15, 4). Thus, it is assumed that all reasonable people would wish to obey the axioms of the theory (47, 36), and that most people actually do, most of the time. The present paper describes several classes of choice problems in which preferences systematically violate the axioms of expected utility theory. In the light of these observations we argue that utility theory, as it is commonly interpreted and applied, is not an adequate descriptive model and we propose an alternative account of choice under risk. 2. CRITIQUE

/pdf/prospect-theory-an-analysis-of-decision-under-risk-4z6oysdahj.pdf

Prospect theory: an analysis of decision under risk

There appears to be general agreement among social psychologists that most human behavior is goal-directed (e. g., Heider, 1958 ; Lewin, 1951). Being neither capricious nor frivolous, human social behavior can best be described as following along lines of more or less well-formulated plans. Before attending a concert, for example, a person may extend an invitation to a date, purchase tickets, change into proper attire, call a cab, collect the date, and proceed to the concert hall. Most, if not all, of these activities will have been designed in advance; their execution occurs as the plan unfolds. To be sure, a certain sequence of actions can become so habitual or routine that it is performed almost automatically, as in the case of driving from home to work or playing the piano. Highly developed skills of this kind typically no longer require conscious formulation of a behavioral plan. Nevertheless, at least in general outline, we are normally well aware of the actions required to attain a certain goal. Consider such a relatively routine behavior as typing a letter. When setting this activity as a goal, we anticipate the need to locate a typewriter, insert a sheet of paper, adjust the margins, formulate words and sentences, strike the appropriate keys, and so forth. Some parts of the plan are more routine, and require less conscious thought than others, but without an explicit or implicit plan to guide the required sequence of acts, no letter would get typed.

From Intentions to Actions: A Theory of Planned Behavior

Studies of risk perception examine the judgements people make when they are asked to characterize and evaluate hazardous activities and technologies. This research aims to aid risk analysis and policy-making by providing a basis for understanding and anticipating public responses to hazards and improving the communication of risk information among lay people, technical experts, and decision-makers. This work assumes that those who promote and regulate health and safety need to understand how people think about and respond to risk. Without such understanding, well-intended policies may be ineffective.

http://science.sciencemag.org/content/sci/236/4799/280.full.pdf

Perception of risk.

It is argued that P-values and the tests based upon them give unsatisfactory results, especially in large samples. It is shown that, in regression, when there are many candidate independent variables, standard variable selection procedures can give very misleading results. Also, by selecting a single model, they ignore model uncertainty and so underestimate the uncertainty about quantities of interest. The Bayesian approach to hypothesis testing, model selection, and accounting for model uncertainty is presented. Implementing this is straightforward through the use of the simple and accurate BIC approximation, and it can be done using the output from standard software. Specific results are presented for most of the types of model commonly used in sociology. It is shown that this approach overcomes the difficulties with P-values and standard model selection procedures based on them. It also allows easy comparison of nonnested models, and permits the quantification of the evidence for a null hypothesis of interest, such as a convergence theory or a hypothesis about societal norms.

https://www.jstor.org/stable/pdfplus/271063.pdf

Bayesian Model Selection in Social Research

Bayesian methods have garnered huge interest in cognitive science as an approach to models of cognition and perception. On the other hand, Bayesian methods for data analysis have not yet made much headway in cognitive science against the institutionalized inertia of 20th century null hypothesis significance testing (NHST). Ironically, specific Bayesian models of cognition and perception may not long endure the ravages of empirical verification, but generic Bayesian methods for data analysis will eventually dominate. It is time that Bayesian data analysis became the norm for empirical methods in cognitive science. This article reviews a fatal flaw of NHST and introduces the reader to some benefits of Bayesian data analysis. The article presents illustrative examples of multiple comparisons in Bayesian analysis of variance and Bayesian approaches to statistical power. Copyright © 2010 John Wiley & Sons, Ltd. For further resources related to this article, please visit the WIREs website.

Bayesian data analysis.

: Twenty-two credit officers from a major California lending institution served as subjects in a criterion validation of multiattribute utility elicitation techniques. The techniques tested were the Holistic Orthogonal Parameter Estimation (HOPE) technique (Barron and Person, 1978), Simple Multiattribute Rating Technique (SMART: Edwards, 1977), point distribution, and three rank weighting techniques as discussed in Stillwell and Edwards, 1979. Equal weighting of importance dimensions was also investigated. The criterion against which the judgments were compared was the lending institutions own credit scoring model. This model is based on statistical analysis of over 8,000 cases from the bank records and is a best fit prediction model. Results demonstrate that subjective judgments of importance weighting show a high degree of agreement in application selection and in total utility realized from that selection. Decomposition techniques did somewhat better than holistic techniques.

/pdf/evaluating-credit-applications-a-validation-of-4c43gfm8he.pdf

Evaluating Credit Applications: A Validation of Multiattribute Utility Techniques Against a Real World Criterion,

The Likelihood Principle of Bayesian inference asserts that only likelihoods matter to single-stage inference. A likelihood is the probability of evidence given a hypothesis multiplied by a positive constant. The constant cancels out of simple versions of Bayes's Theorem, and so is irrelevant to single-stage inferences.



Most non-statistical inferences require a multi-stage path from evidence to hypotheses; testimony that an event occurred does not guarantee that in fact it did. Hierarchical Bayesian models explicate such cases. For such models, the Likelihood Principle applies to a collection of data elements treated as a single datum conditionally independent of other similar collections. It does not necessarily apply to a single data element taken alone. This has unfortunate implications; in particular, it does not permit the inputs to Bayesian arithmetic at all levels to be likelihood ratios.



These issues are sorted out in the context of a trial in which one author is accused of murdering another, with the third as a key witness.

Murder and (of?) the likelihood principle: A Trialogue

: Three procedures for constructing additive multi-attribute utility theory, (MAUT) models were tested for their differential validity: a probabilistic procedure, a simple direct rating procedure, and a modified direct rating procedure. Validation criteria were ratings and simple choices. Procedures were evaluated after an intensive training session in which subjects learned to adopt an evaluation strategy with which they felt most comfortable and which best reflected their preferences. The results of a correlational analysis indicated that MAUT can improve upon the decision maker's own unaided intuition. The probabilistic procedure was found to be the superior method for predicting simple choices between stimuli.

Evaluation of Complex Stimuli Using Multi-Attribute Utility Procedures

The averaging of scores differs from the averaging of numbers in that behavioral issues are built into scores. The behavioral issues are the weight attached to a score and the metric on which the scores have been gathered. A single equation is proposed, derived from Aczel's (1966) model of the quasilinear mean, that encompasses the standard measures of central tendency. The equation allows for differential weighting of scores and also addresses the metric issue by incorporating response transformation.

/pdf/a-mean-for-all-seasons-14o2qbqsas.pdf

A mean for all seasons.

This paper reports the first-year results of a two-year study exploring whether a Multi-Attribute Utility (MAU) model that includes a new momentary salience parameter can predict smoking and alcohol use among an ethnically diverse Southern California sample of 2,789 7th graders. The model allows detailed investigation of the role that perceptions regarding ten anticipated consequences of substance use (e.g., being more popular, feeling more relaxed, contracting a devastating illness in the future) play in the decision to initiate substance use. The student was asked about either alcohol or tobacco, but not both. Students self-reported their views regarding the consequences, along with a history of their usage, on a paper-and-pencil questionnaire administered in either a traditional classroom setting or a simulated party setting. While most students had not initiated usage at this time, those who had already begun smoking had significantly higher MAUs than nonsmokers, but there was no difference for alcohol usage. The manipulation of setting had no effect.

/pdf/the-puzzle-of-adolescent-substance-initiation-mk2cozxowa.pdf

Ward Edwards

Papers

Evaluating Credit Applications: A Validation of Multiattribute Utility Techniques Against a Real World Criterion,

Murder and (of?) the likelihood principle: A Trialogue

Evaluation of Complex Stimuli Using Multi-Attribute Utility Procedures

A mean for all seasons.

The Puzzle of Adolescent Substance Initiation