带有辅助信息对数变换模型的违约预报

本文考虑对数变换的逻辑模型以刻画不同的违约概率曲线,研究如何将辅助信息加入到模型的估计中以提高违约估计的稳定性和效率.通过非参数经验似然,提出模型参数统计推断方法,并推导估计的相合性和渐近正态性.从理论上证明添加了辅助信息的估计的有效性,并且模拟表明该方法能够很好地提升估计的效率,另外也通过模拟讨论辅助信息的影响.将所提出的方法应用于ST (special treatment)股票的数据,实证结果表明,加入了辅助信息的参数估计更加有效.

Default forecast with auxiliary information using a logarithmic transformation model

This paper studies how to integrate auxiliary information into the estimation procedure to improve the stability and efficiency of estimators for default forecast and introduces a log-transformation logic model to characterize different default probability curves. In this paper, we establish the consistency and asymptotic normality of the estimators and prove the efficiency of the proposed estimators with auxiliary information. Simulation results show that the proposed method can improve the efficiency of estimation and the influence of auxiliary information is discussed. We apply the proposed method to the data of ST(special treatment) stocks, and the empirical results show that the parameter estimation with auxiliary information is more effective.