ANALYSIS OF UNBIASED ESTIMATORS USING GEOMETRIC FAILURE DATA.
Abstract
An important example of an event which obeys the geometric probability law with parameter theta is the number of cycles required to obtain the first failure of an item, where the success of each cycle is independent with probability of success theta. The true probability of success, in manufactured items, is usually unknown and must be estimated on the basis of observed data obtained from a test of sample items. An important estimator for this probability is the unbiased estimator, defined as that estimator whose expected value equals the true value of the parameter. In this study, an unbiased estimator for theta is derived. This estimator is based on the results of a series of independent items, each cycled to first failure. Series approximations for the variance of this estimator are derived, and some values of the variance are tabled for those cases thought to be of special interest. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1964
- Accession Number
- AD0481357
Entities
People
- Herman C. Quitmeyer
Organizations
- Naval Postgraduate School