EXPONENTIAL LIFE TEST PROCEDURES WHEN THE DISTRIBUTION HAS MONOTONE FAILURE RATE
Abstract
A number of estimates and tests for mean life and other parameters derived under the exponential distribution assumption are studied under the alternative condition that the distribution has increasing (decreasing) failure rate. The estimates considered are, for the most part, based on censored and truncated samples. It is shown that these estimates generally favor the producer (consumer) in the IFR (DFR) case. Properties of order statistics and their spacings from distributions with increasing (decreasing) failure rate are presented.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 1964
- Accession Number
- AD0610593
Entities
People
- Frank Proschan
- Richard E. Barlow
Organizations
- University of California, Berkeley