An improved and efficient biased estimation technique in logistic regression model. Issue 9 (2nd May 2020)

• Record Type: Journal Article
• Authors: Asar, Yasin; Wu, Jibo
• Is Part Of: Communications in statistics. Volume 49:Issue 9(2020)
• Page Start: 2237
• Page End: 2252
• Publication Date: 2020-05-02
• Subjects: Restricted maximum likelihood estimator -- Restricted Liu-type estimator -- Modified restricted Liu-type estimator -- Logistic regression model; 62J05 -- 62J07; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2019.1568494
• Languages: English
• ISSNs: 0361-0926

Abstract

Abstract: In this article, we propose a new improved and efficient biased estimation method which is a modified restricted Liu-type estimator satisfying some sub-space linear restrictions in the binary logistic regression model. We study the properties of the new estimator under the mean squared error matrix criterion and our results show that under certain conditions the new estimator is superior to some other estimators. Moreover, a Monte Carlo simulation study is conducted to show the performance of the new estimator in the simulated mean squared error and predictive median squared errors sense. Finally, a real application is considered.