Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1150028 | Journal of Statistical Planning and Inference | 2007 | 11 Pages |
Abstract
Asymptotic behavior of a log-likelihood ratio statistic for testing a change in a three parameter Weibull distribution is studied. It is shown that if a shape parameter α>2α>2 the law of iterated logarithm for maximum-likelihood estimators is still valid and the log-likelihood testing statistic is asymptotically distributed (after an appropriate normalization) according to a Gumbel distribution.
Related Topics
Physical Sciences and Engineering
Mathematics
Applied Mathematics
Authors
Daniela Jarušková,