Optimal Warranty Length for a Weibull Distributed Product with Progressive Censoring
- 2013-04-22 (Mon.), 10:30 AM
- Recreation Hall, 2F, Institute of Statistical Science
- Prof. Shuo-Jye Wu
- Department of Statistics, Tamkang University
Abstract
In the intensely competitive market, one way by which manufacturers attract consumers to their products is by providing warranties on the products. Consumers are willing to purchase a high-price product only if they can be assured about product reliability. Product with a longer warranty period usually indicates better reliability. However, offering an unlimited warranty is unrealistic since maintaining such a policy needs very high cost. In this article, we investigate a decision problem under the warranty which is a combination of free-replacement and pro-rata policies. We use Bayesian approach to determine the optimal warranty lengths. The Weibull distribution is employed to describe the product lifetime and the progressive censoring is applied to collect the data. An example is presented for illustration. (This is a joint research with Syuan-Rong Huang)