Přístupnostní navigace
E-application
Search Search Close
Publication detail
FUSEK, M. MICHÁLEK, J.
Original Title
T-test alternative for multiply left-censored samples from Weibull distribution
Type
conference paper
Language
English
Original Abstract
Left-censored data with one or more detection limits occur frequently in many application areas. This paper suggests a computational procedure for calculation of maximum likelihood estimates of parameters for type I multiply left-censored Weibull samples. Moreover, using the asymptotic properties of maximum likelihood estimates, an alternative to classic t-test that can be used for comparison of expected values of two independent type I multiply left-censored Weibull samples is proposed. The power functions of both tests are compared by simulations. The methods derived in this paper can be used in real environmental or chemical data analysis.
Keywords
Fisher information matrix, maximum likelihood, power function of test, t-test
Authors
FUSEK, M.; MICHÁLEK, J.
RIV year
2015
Released
23. 6. 2015
ISBN
1803-3814
Periodical
Mendel Journal series
State
Czech Republic
Pages from
169
Pages to
174
Pages count
6
BibTex
@inproceedings{BUT115030, author="Michal {Fusek} and Jaroslav {Michálek}", title="T-test alternative for multiply left-censored samples from Weibull distribution", booktitle="21st International Conference on Soft Computing - MENDEL 2015", year="2015", journal="Mendel Journal series", pages="169--174", issn="1803-3814" }