Group decision in bayesian sampling inspection plans
| Autor: | 黃郁琇 |
|---|---|
| Rok vydání: | 2002 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 90 There are lots of studies with sampling inspection plans in literature. No matter how the events belong to “one decision maker problem” or “decision between adversaries problem”, decision makers presume that the prior distribution of parameters are conjugate prior distributions. From this point of view, it is effective to solve some problems encountered. However, for the rapidly changing world in all aspects, it is effective and efficient to make “group decision” for running a business. If we can integrate the opinions from many experts for making decisions, it should be advantageous to make correct decisions. Based on the above prerequisites, in this study, we carry out the sampling inspection plans with the group decision under the Bayesian framework. Assuming one decision group is composed of k experts, and the parameter involved in the sample inspection plans is a random variable. For the i-th expert of the decision group,respectively, with the weight wi, where wi are grater then 0,and summation is 1. Therefore, integrating the recognitions from k experts, we acquire a new prior distribution. In addition to discussing the relationships between the normal distribution and the exponential distribution in the conjugate prior distribution, we propose a loss function suitable for the decision-making problem. Then, we calculate Bayes risk values related to our loss function and we obtain the most optimal sample size. Meanwhile, we try to understand the decision-making behaviors under minimum Bayes risk by simulating the related decisions. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|