Robust Brown-Forsythe and Robust Modified Brown-Forsythe ANOVA Tests Under Heteroscedasticity for Contaminated Weibull Distribution
Fuente:
Redalyc
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Artículo científico |
| Lingua: | en |
| Pubblicazione: |
Universidad Nacional de Colombia
2016
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1876430207762563072 |
|---|---|
| author | Derya Karagöz |
| author_facet | Derya Karagöz |
| contents | Robust Brown-Forsythe and Robust Modified Brown-Forsythe ANOVA Tests Under Heteroscedasticity for Contaminated Weibull Distribution Derya Karagöz Tülay Saraçbaşı Física, Astronomía y Matemáticas Brown ANOVA Forsythe Modified Brown WeibullDistribution In this study, robust Brown-Forsythe and robust Modified Brown-ForsytheANOVA tests are proposed to take into consideration heteroscedastic andnon-normality data sets with outliers. The non-normal data is assumed to bea two parameters Weibull distribution. Robust proposed tests are obtainedby using robust mean and variance estimators based onmedian=M ADandmedian=Qnmethods instead of maximum likelihood. The behaviors of therobust proposed and classical ANOVA tests are examined by simulationstudy. The results shows that the proposed robust tests have good per-formance especially in the presence of heteroscedasticity and contamination. 2016 artículo científico 0120-1751 https://www.redalyc.org/articulo.oa?id=89943490002 en http://www.redalyc.org/revista.oa?id=899 Revista Colombiana de Estadística application/pdf Universidad Nacional de Colombia Revista Colombiana de Estadística (Colombia) Num.1 Vol.39 |
| format | Artículo científico |
| id | redalyc_89943490002 |
| institution | Redalyc |
| language | en |
| publishDate | 2016 |
| publisher | Universidad Nacional de Colombia |
| spellingShingle | Robust Brown-Forsythe and Robust Modified Brown-Forsythe ANOVA Tests Under Heteroscedasticity for Contaminated Weibull Distribution Derya Karagöz Física, Astronomía y Matemáticas Brown ANOVA Forsythe Modified Brown WeibullDistribution Robust Brown-Forsythe and Robust Modified Brown-Forsythe ANOVA Tests Under Heteroscedasticity for Contaminated Weibull Distribution Derya Karagöz Tülay Saraçbaşı Física, Astronomía y Matemáticas Brown ANOVA Forsythe Modified Brown WeibullDistribution In this study, robust Brown-Forsythe and robust Modified Brown-ForsytheANOVA tests are proposed to take into consideration heteroscedastic andnon-normality data sets with outliers. The non-normal data is assumed to bea two parameters Weibull distribution. Robust proposed tests are obtainedby using robust mean and variance estimators based onmedian=M ADandmedian=Qnmethods instead of maximum likelihood. The behaviors of therobust proposed and classical ANOVA tests are examined by simulationstudy. The results shows that the proposed robust tests have good per-formance especially in the presence of heteroscedasticity and contamination. 2016 artículo científico 0120-1751 https://www.redalyc.org/articulo.oa?id=89943490002 en http://www.redalyc.org/revista.oa?id=899 Revista Colombiana de Estadística application/pdf Universidad Nacional de Colombia Revista Colombiana de Estadística (Colombia) Num.1 Vol.39 |
| title | Robust Brown-Forsythe and Robust Modified Brown-Forsythe ANOVA Tests Under Heteroscedasticity for Contaminated Weibull Distribution |
| topic | Física, Astronomía y Matemáticas Brown ANOVA Forsythe Modified Brown WeibullDistribution |
| url | https://www.redalyc.org/articulo.oa?id=89943490002 |