Optimal generalized logistic estimator

ABSTRACT

In this paper, we propose a new efficient estimator namely Optimal Generalized Logistic Estimator (OGLE) for estimating the parameter in a logistic regression model when there exists multicollinearity among explanatory variables. Asymptotic properties of the proposed estimator are also derived. The performance of the proposed estimator over the other existing estimators in respect of Scalar Mean Square Error criterion is examined by conducting a Monte Carlo simulation.

KEYWORDS:

• Logistic regression
• Multicollinearity
• Biased estimator
• Optimal generalized logistic estimator
• Scalar mean square error.