DocumentCode :
585221
Title :
Estimator based on percentiles for log-logistic distribution
Author :
Arik, I. ; Kantar, Y.M.
Author_Institution :
Fac. of Sci., Dept. of Stat., Anadolu Univ., Eskisehir, Turkey
fYear :
2012
fDate :
10-12 Sept. 2012
Firstpage :
1
Lastpage :
5
Abstract :
In this study, we consider the estimator based on percentiles for log-logistic distribution similar to the study of [6] and we also graph breakdown plots of the estimators that are considered below to have an opinion about robustness properties. The estimator based on percentiles is explicit functions of sample percentiles, thus, easy to compute and do not involve any iterative computational complexities like Maximum likelihood estimator (MLE). The simulation results show that the considered estimator performs better than MLE for small sample sizes.
Keywords :
estimation theory; graph theory; estimator graph breakdown plots; log-logistic distribution percentile explicit functions; robustness properties; Analytical models; Electric breakdown; Least squares approximation; Maximum likelihood estimation; Robustness; Shape; least squares; log-logistic distribution; maximum likelihood; percentile;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Statistics in Science, Business, and Engineering (ICSSBE), 2012 International Conference on
Conference_Location :
Langkawi
Print_ISBN :
978-1-4673-1581-4
Type :
conf
DOI :
10.1109/ICSSBE.2012.6396637
Filename :
6396637
Link To Document :
بازگشت