Research Reports from the Department of Operations
Document Type
Report
Publication Date
1-1-1964
Abstract
A special instance of the general problem of decision-making under uncertainty is considered. In the absence of a well-defined utility function, the following method is adopted: First, a "reasonable" or "acceptable" policy is chosen with unspecified parameters. Then, the associated decision rule is formulated; typically, these are functional transforms of appropriate state variables. Analysis is made of the outcomes produced by the rule in conjunction with the stochastic price process. Finally, some functionals of the (random) outcomes are computed with a view to obtain measures of performance of the decision rule. In each case, the derivations indicate the dependence of the measures (of performance) on the unspecified parameters. The analysis will be employed (in a later Memorandum in this series) to (a) compare alternative decision rules on the basis of a given index of performances and (b) develop a single utility function from the trade-offs between the levels of performance measured in several ways. [Likely published circa 1964.]
Keywords
Operations research, Markov processes, Decision making--Mathematical models, Uncertainty--Mathematical models, Stochastic processes, Utility theory, Functional analysis
Publication Title
Technical Memorandums from the Department of Operations, School of Management, Case Western Reserve University
Issue
Technical memorandum no. 15
Rights
This work is in the public domain and may be freely downloaded for personal or academic use
Recommended Citation
Treviño, José and Sengupta, S. Sankar, "Some Order Statistics Relating to Markov Chains: An Application to Purchasing Policies" (1964). Research Reports from the Department of Operations. 542.
https://commons.case.edu/wsom-ops-reports/542