A Computational Technique For Maximum Likelihood Estimation With Weibull Models

作者: Norman P. Archer

DOI: 10.1109/TR.1980.5220713

关键词:

摘要: An improved computational technique has been developed for use in the maximum likelihood estimation of Weibull parameters complete, censored or grouped data, 3-parameter model. To demonstrate technique, a limited set Monte Carlo results are given which compare actual covariance matrix parameter estimates with an approximation to this using negative inverse empirical information matrix. The approximation, suggested by several authors, is examined both and standard 2-parameter particular cases censored, samples sizes.

参考文章(12)
Larry J. Ringer, Edgar E. Sprinkle, Estimation of the Parameters of the Weibull Distribution from Multicensored Samples IEEE Transactions on Reliability. pp. 46- 51 ,(1972) , 10.1109/TR.1972.5216171
Howard Rockette, Charles Antle, Lawrence A. Klimko, Maximum Likelihood Estimation with the Weibull Model Journal of the American Statistical Association. ,vol. 69, pp. 246- 249 ,(1974) , 10.1080/01621459.1974.10480164
J. Edward Bilikam, Albert H. Moore, Estimation of Mission Reliability from Multiple Independent Grouped Censored Samples IEEE Transactions on Reliability. ,vol. R-26, pp. 57- 60 ,(1977) , 10.1109/TR.1977.5215076