Probabilistic Measures of Adequacy of a Numerical Search for a Global Maximum
作者:
StephenJ. Finch,
NancyR. Mendell,
HenryC. Thode,
期刊:
Journal of the American Statistical Association
(Taylor Available online 1989)
卷期:
Volume 84,
issue 408
页码: 1020-1023
ISSN:0162-1459
年代: 1989
DOI:10.1080/01621459.1989.10478867
出版商: Taylor & Francis Group
关键词: Maximum likelihood;Mixture of normal distributions;Numerical optimization;Simulated annealing;Unobserved species
数据来源: Taylor
摘要:
Measures of the probability of all unobserved species are applied to the problem of assessing the adequacy of a search for a global maximum using random starting points. The measures, as used here, estimate the probability that an iterative algorithm using a randomly selected starting point will find a solution not observed in previous random starting points. The probability of an unobserved global maximum is less than or equal to this probability. We used these measures to evaluate the adequacy of our search procedure for the maximum likelihood estimates of the parameters of a mixture of two normals. These measures indicated that for most problems generated there was little chance that there were unobserved domains of convergence. Occasional problems, however, had appreciable estimated probabilities. In such problems, examination of the data suggested regions where a more focused search for unobserved domains of convergence was warranted.
点击下载:
PDF (653KB)
返 回