ELTE logo ELTE Eötvös Loránd University
ANNALES Universitatis Scientiarum Budapestinensis de Rolando Eötvös Nominatae
Sectio Computatorica

Volumes » Volume 45 (2016)

https://doi.org/10.71352/ac.45.045

Competing risks Weibull model: parameter
estimates and their accuracy

Ágnes M. Kovács and Howard M. Taylor

Abstract. Competing risks Weibull model arises as the distribution of the minimum of two independent (two parameter) Weibull random variables having distinct Weibull exponents. This model is commonly used in the strength testing of certain brittle fibers, but it also appears in modeling the life of a series system determined by the shortest of its components. We implemented the EM algorithm to estimate the bi-Weibull model parameters (when the failure mode is unknown) and we explicitly derived the observed information matrix to address the precision of these estimates.

Full text PDF
Journal cover