This dissertation addresses the question of choosing the best information alternative in engineering decisions. The decision maker maximizes his expected utility under uncertainty where both the action he takes and the state of the environment determines the payoff earned. The decision maker has an opportunity to gather information about the decision environment a priori at a certain cost. There might be different information alternatives, and the decision maker has to determine which alternative offers "better" prospects for improving the decision.
Any decision environment that is characterized by a finite number of outcomes and a discrete probability distribution over the set of outcomes is a lottery. We analyze the value of information on a single outcome and determine the attributes in each piece of information that maximizes its value. Information is valuable when the decision is changed after gathering information. We show that if the number of optimal actions taken under different outcomes scenarios is finite, the decision maker does not require the perfect information. Further, we analyze the relation between the value of information and its determinants, and show a monotonic relation exists for a restricted class of information bundles and utility functions. We use different approaches to evaluate information and analyze the cases where preference reversals occur between different approaches. We observe that a priori pricing of information does not necessarily induce the same ranking with the expected utility approach, however both approaches agree on whether a given piece of information is valuable or not.
The second part of this dissertation evaluates information in both static and dynamic coinsurance problems. In static insurance decisions, we analyze the case where the decision maker gathers information about the severity of the risk events and perform ranking of information bundles in a specific class. In dynamic insurance problems, we make a case study to analyze different physical risks that the production facilities are exposed to. The information in dynamic insurance problems involves more detail with regard to the timing of the multiple risk events. We observe that information on events that pose relatively good scenarios for the decision maker have value, however, their value may diminish as their probability of occurance decreases. The decision maker purchases more information as the profitability of the product increases and less information as the initial wealth increases. Furthermore, the decrease cost of insurance does not necessarily make information more valuable as the value is directly related to the change in the decisions rather than the cost of taking a specific action.
Identifer | oai:union.ndltd.org:tamu.edu/oai:repository.tamu.edu:1969.1/1075 |
Date | 15 November 2004 |
Creators | Bakir, Niyazi Onur |
Contributors | Klutke, Georgia-Ann |
Publisher | Texas A&M University |
Source Sets | Texas A and M University |
Language | en_US |
Detected Language | English |
Type | Electronic Dissertation, text |
Format | 619616 bytes, 180196 bytes, electronic, application/pdf, text/plain, born digital |
Page generated in 0.002 seconds