Suchergebnisse

AbstractAlthough there has been considerable research directed toward developing Bayesian acceptance sampling plans, little consideration has been given to incorporating a decision‐maker's risk attitude or treating such problems in terms of multiple‐type defects and multiple criteria. We review our own work which is focused on the above issues. A model incorporating risk preference is shown to yield substantial differences in the characteristics of an optimal sampling plan relative to a typical Bayesian linear cost (risk neutral) model. Bayesian models and optimization schemes for a variety of multiple‐type defect plans are reviewed. A bicriterion acceptance model, employing average outgoing quality and average inspection cost is also formulated. Traditional versus interactive optimization procedures are compared empirically in terms of ease of use, satisfaction with solutions, and insight gained into the problem.

ABSTRACTThis paper reports the results of an experiment which investigated the effects of various ways of structuring decision problems under uncertainty (viz, matrix, tree, versus word representations) and various forms of feedback (discussion versus non‐discussion of prepared answers conforming to and deviating from the irrelevance of identical outcomes postulate) on consistent choice behavior (i.e., in accordance with this postulate) in the context of Allais and Morlat‐type (A & M) problems. The special structure of A & M problems is especially useful for studying such behavior in that it presumably leads to a set of choices that violates this fundamental norm of decision theory. The experiment involved 134 industrial management undergraduates who gambled to improve their grades in a statistics course. The results showed that: (1) structuring such problems as "decision trees" or "decision matrices" had either a detrimental or no beneficial effect respectively on the number of consistent responses; while (2) discussion led to some improvement in consistency over no discussion. The implications of the findings for training in rational decision making are discussed.

ABSTRACTA preference‐order recursion algorithm for obtaining a relevant subset of pure, admissible (non‐dominated, efficient) decision functions which converges towards an optimal solution in statistical decision problems is proposed. The procedure permits a decision maker to interactively express strong binary preferences for partial decision functions at each stage of the recursion, from which an imprecise probability and/or utility function is imputed and used as one of several pruning mechanisms to obtain a reduced relevant subset of admissible decision functions or to converge on an optimal one. The computational and measurement burden is thereby mitigated significantly, for example, by not requiring explicit or full probability and utility information from the decision maker. The algorithm is applicable to both linear and nonlinear utility functions. The results of behavioral and computational experimentation show that the approach is viable, efficient, and robust.

ABSTRACTVarious approaches have been proposed for determining scenario probabilities to facilitate long‐range planning and decision making. These include microlevel approaches based on the analysis of relevant underlying events and their interrelations and direct macrolevel examination of the scenarios. The determination of a unique solution demands excessive consistency and time requirements on the part of the expert and often is not guaranteed by these procedures. We propose an interactive information maximizing scenario probability query procedure (IMQP) that exploits the desirable features of existing methods while circumventing their drawbacks. The approach requires elicitation of cardinal probability assessments and bounds for only marginal and first‐order conditional events, as well as ordinal probability comparisons (probability orderings or rankings) of carefully selected scenario subsets determined using concepts of information theory. Guidelines for implementation based on simulation results are also developed. A goal program for handling inconsistent ordinal probability responses is also integrated into the procedure. The results of behavioral experimentation (which compared our approach to Expert Choice and showed that the IMQP was viable) compared favorably in terms of ease of use and time requirements, and works best for problems with a large number of scenarios. Design modifications to IMQP learned from the experiments, such as incorporating interactive graphics, are also in progress.

Twelve males were tested under a control and two alcohol treatments in a perimeter apparatus used for testing peripheral vision. They were required to fixate either on a steady-state central fixation light and detect peripheral lights, or to count blinks produced by the cessations of the fixation light and to detect peripheral lights. Alcohol produced an impairment of peripheral vision only under conditions where the central fixation light blinked and thus required information processing. No performance decrement occurred when the central light did not blink. The results suggest that alcohol interferes with central information processing rather than peripheral sensory mechanisms.