Resampling Techniques for Estimating the Parameters of Grubbs Model with Asymmetric Heavy-Tailed Distributions | ||||
| The Egyptian Statistical Journal | ||||
| Article 6, Volume 61, Issue 2, December 2017, Page 125-139 PDF (5.17 MB) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/esju.2017.270129 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| Amany Mousa; Hanadi Mansour* | ||||
| Institute of Statistical Studies and Research- Cairo University, Egypt | ||||
| Abstract | ||||
| In this paper, three resampling techiques are considered, namely, bootstrap, jack-knife and jackknife after bootstrap. The main objective is to study the performance of these techniques for maximum likehood estimation for the parameters using expectation conditional maximization either (ECME)algorithm for Grubbs model when the latent response follows asymmetric heavy – tailed distributions such as scale mixture of skew normal distributions (such as skew-t (ST), skew Slash (SSL) , skew contaminated normal (SCN). Also, the performance of these techniques id discussed for detection of the influential observations using local influence method for assessing the robustness of these parameter estimates under different perturbation schemes for Grubbs model. The performance is illustrated through an application using real data set under different bootstrap replications. Our results provide resampling techniques with better fit, protect against outlying observations and more precise inferences than tranditional techniques | ||||
| Keywords | ||||
| Expectation conditional maximization; Grubbs model; Scale mixture; Skew normal distributions | ||||
|
Statistics Article View: 138 PDF Download: 265 |
||||
