The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression
This article is concerned with the performance of the maximum estimated likelihood estimator in the presence of separation in the space of the independent variables and high leverage points. The maximum likelihood estimator suffers from the problem of non overlap cases in the covariates where the re...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
AIP Publishing LLC
2014
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/57382/1/The%20effect%20of%20high%20leverage%20points%20on%20the%20maximum%20estimated%20likelihood%20for%20separation%20in%20logistic%20regression.pdf |
| _version_ | 1825931601454825472 |
|---|---|
| author | Ariffin @ Mat Zin, Syaiba Balqish Midi, Habshah Arasan, Jayanthi Rana, Md. Sohel |
| author_facet | Ariffin @ Mat Zin, Syaiba Balqish Midi, Habshah Arasan, Jayanthi Rana, Md. Sohel |
| author_sort | Ariffin @ Mat Zin, Syaiba Balqish |
| collection | UPM |
| description | This article is concerned with the performance of the maximum estimated likelihood estimator in the presence of separation in the space of the independent variables and high leverage points. The maximum likelihood estimator suffers from the problem of non overlap cases in the covariates where the regression coefficients are not identifiable and the maximum likelihood estimator does not exist. Consequently, iteration scheme fails to converge and gives faulty results. To remedy this problem, the maximum estimated likelihood estimator is put forward. It is evident that the maximum estimated likelihood estimator is resistant against separation and the estimates always exist. The effect of high leverage points are then investigated on the performance of maximum estimated likelihood estimator through real data sets and Monte Carlo simulation study. The findings signify that the maximum estimated likelihood estimator fails to provide better parameter estimates in the presence of both separation, and high leverage points. |
| first_indexed | 2024-03-06T09:29:13Z |
| format | Conference or Workshop Item |
| id | upm.eprints-57382 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T09:29:13Z |
| publishDate | 2014 |
| publisher | AIP Publishing LLC |
| record_format | dspace |
| spelling | upm.eprints-573822017-09-27T07:03:19Z http://psasir.upm.edu.my/id/eprint/57382/ The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression Ariffin @ Mat Zin, Syaiba Balqish Midi, Habshah Arasan, Jayanthi Rana, Md. Sohel This article is concerned with the performance of the maximum estimated likelihood estimator in the presence of separation in the space of the independent variables and high leverage points. The maximum likelihood estimator suffers from the problem of non overlap cases in the covariates where the regression coefficients are not identifiable and the maximum likelihood estimator does not exist. Consequently, iteration scheme fails to converge and gives faulty results. To remedy this problem, the maximum estimated likelihood estimator is put forward. It is evident that the maximum estimated likelihood estimator is resistant against separation and the estimates always exist. The effect of high leverage points are then investigated on the performance of maximum estimated likelihood estimator through real data sets and Monte Carlo simulation study. The findings signify that the maximum estimated likelihood estimator fails to provide better parameter estimates in the presence of both separation, and high leverage points. AIP Publishing LLC 2014 Conference or Workshop Item PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/57382/1/The%20effect%20of%20high%20leverage%20points%20on%20the%20maximum%20estimated%20likelihood%20for%20separation%20in%20logistic%20regression.pdf Ariffin @ Mat Zin, Syaiba Balqish and Midi, Habshah and Arasan, Jayanthi and Rana, Md. Sohel (2014) The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression. In: 2nd ISM International Statistical Conference 2014 (ISM-II), 12-14 Aug. 2014, MS Garden Hotel, Kuantan, Pahang. (pp. 402-408). 10.1063/1.4907472 |
| spellingShingle | Ariffin @ Mat Zin, Syaiba Balqish Midi, Habshah Arasan, Jayanthi Rana, Md. Sohel The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression |
| title | The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression |
| title_full | The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression |
| title_fullStr | The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression |
| title_full_unstemmed | The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression |
| title_short | The effect of high leverage points on the maximum estimated likelihood for separation in logistic regression |
| title_sort | effect of high leverage points on the maximum estimated likelihood for separation in logistic regression |
| url | http://psasir.upm.edu.my/id/eprint/57382/1/The%20effect%20of%20high%20leverage%20points%20on%20the%20maximum%20estimated%20likelihood%20for%20separation%20in%20logistic%20regression.pdf |
| work_keys_str_mv | AT ariffinmatzinsyaibabalqish theeffectofhighleveragepointsonthemaximumestimatedlikelihoodforseparationinlogisticregression AT midihabshah theeffectofhighleveragepointsonthemaximumestimatedlikelihoodforseparationinlogisticregression AT arasanjayanthi theeffectofhighleveragepointsonthemaximumestimatedlikelihoodforseparationinlogisticregression AT ranamdsohel theeffectofhighleveragepointsonthemaximumestimatedlikelihoodforseparationinlogisticregression AT ariffinmatzinsyaibabalqish effectofhighleveragepointsonthemaximumestimatedlikelihoodforseparationinlogisticregression AT midihabshah effectofhighleveragepointsonthemaximumestimatedlikelihoodforseparationinlogisticregression AT arasanjayanthi effectofhighleveragepointsonthemaximumestimatedlikelihoodforseparationinlogisticregression AT ranamdsohel effectofhighleveragepointsonthemaximumestimatedlikelihoodforseparationinlogisticregression |