Inference and Prediction for a General Order Statistic Model with Unknown Population Size.
Abstract
Suppose that the first n order statistics from a random sample of N positive random variables are observed, where N is unknown. A Bayes empirical Bayes approach to inference is presented. This permits the comparison of competing, perhaps non-nested, models in a natural way, and also provides easily implemented inference and prediction procedures which avoid the difficulties of non-Bayesian methods. Applications to three software reliability data sets indicate that the much-used exponential order statistic model may give rather optimistic estimates of system reliability, while the, not previously considered, Weibull order statistic model seems promising for such applications. Keywords: Pareto order statistic model; Software reliability.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1986
- Accession Number
- ADA181394
Entities
People
- Adrian Raftery
Organizations
- University of Washington