Performance of New Liu-type Logistic Estimators in Combating Multicollinearity

Authors

Samah N. Yussef, Department of Applied Statistics and Econometrics, Faculty of Graduate Studies for Statistical Research, 12613 Cairo University, Cairo, EgyptFollow
Ahmed H. Youssef, Department of Applied Statistics and Econometrics, Faculty of Graduate Studies for Statistical Research, 12613 Cairo University, Cairo, EgyptFollow
Abdel Latif S. H., Department of Applied Statistics and Econometrics, Faculty of Graduate Studies for Statistical Research, 12613 Cairo University, Cairo, EgyptFollow

Abstract

Multicollinearity problem in logistic regression causes an inflation in the variance of the Maximum Likelihood (ML) estimator. To overcome this serious problem, some biased estimators such as: ridge estimator, Liu estimator and Liu-type estimator, were suggested as a way of having smaller Mean Squared Error (MSE) than ML estimator. This paper discusses these different biased estimators in the logistic regression and proposes some new ridge estimators by Mansson(2012) and Asar(2016) to be applied in the Liu-type estimators. A Monte Carlo simulation study was conducted to assess the performances of ridge and Liu-type estimators in the sense of MSE and Bias criteria. It was concluded that the new estimators perform well in the Liu-type estimation.

Digital Object Identifier (DOI)

http://dx.doi.org/10.18576/jsap/110325

Recommended Citation

N. Yussef, Samah; H. Youssef, Ahmed; and Latif S. H., Abdel (2022) "Performance of New Liu-type Logistic Estimators in Combating Multicollinearity," Journal of Statistics Applications & Probability: Vol. 11: Iss. 3, Article 25.
DOI: http://dx.doi.org/10.18576/jsap/110325
Available at: https://digitalcommons.aaru.edu.jo/jsap/vol11/iss3/25