期刊
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
卷 42, 期 7, 页码 1578-1586出版社
TAYLOR & FRANCIS INC
DOI: 10.1080/03610918.2012.667480
关键词
Liu-type estimator; Logistic regression; Multicollinearity; Ridge estimator
It is known that multicollinearity inflates the variance of the maximum likelihood estimator in logistic regression. Especially, if the primary interest is in the coefficients, the impact of collinearity can be very serious. To deal with collinearity, a ridge estimator was proposed by Schaefer et al. The primary interest of this article is to introduce a Liu-type estimator that had a smaller total mean squared error (MSE) than the Schaefer's ridge estimator under certain conditions. Simulation studies were conducted that evaluated the performance of this estimator. Furthermore, the proposed estimator was applied to a real-life dataset.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据