摘要
本文将多项Probit模型推广到更一般的形式,研究了推广的多项Probit模型的逆回归性质,给出了回归系数的逆回归估计方法,并证明了在满足一些条件时估计是渐近正态的.模拟表明逆回归估计方法有良好的表现.
In this paper, we generalize the Multinomial Probit Model and investigate the inverse regression of the Generalized Multinomial Probit Model. A method of inverse regression is proposed for estimating the regression coefficient. Under some assumptions we obtain the asymptotic normality of the estimate. The result of simulation shows that the method performs well.
出处
《应用概率统计》
CSCD
北大核心
2008年第5期501-512,共12页
Chinese Journal of Applied Probability and Statistics
关键词
多项Probit模型
逆回归方法
回归系数的估计
渐近正态性
Multinomial Probit model, method of inverse regression, estimation for regression coefficient, asymptotic normality.
