Inference from Accelerated Life Tests Using Eyring Type Re-Parameterizations.
Abstract
Least squares estimators of the parameters of the generalized Eyring Model are obtained using data from censored life tests conducted at several accelerated environments. These estimators are obtained after establishing that the Gauss-Markov conditions for least squares estimation are satisfied. Confidence intervals for the hazard rate at use conditions are obtained after empirically showing that the logarithm of the estimate of the hazard rate at use conditions is approximately normally distributed. The coverage probabilities of the confidence intervals are also verified by a Monte Carlo experiment. The techniques are illustrated by an application to some real data. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 16, 1974
- Accession Number
- AD0778641
Entities
People
- Donald Y. Goldschen
- Nozer Singpurwalla
- Victor F. Castellino
Organizations
- George Washington University