基于二元选择分位数回归的上市公司信用评估

Credit evaluation of listed company via binary quantile regression approach

二元选择分位数回归是二元选择均值回归在分位数框架下的推广,能够更好地揭示解释变量对响应变量在不同分位点处的异质影响,从而可以更加准确地描述与预测二元选择行为。文章基于二元选择分位数回归建立了上市公司信用评估方法,通过数值模拟和实证研究,对二元选择分位数回归与二元选择均值回归的信用评估能力进行了比较。研究结果表明,无论样本内还是样本外,二元选择分位数回归均能够更加准确地评估上市公司的信用状况。

Binary quantile regression,which extends the binary mean regression to quantile framework, can reveal the heterogeneous effect of independent variables on the response variable across different quantiles. Therefore,it can describe and predict the behavior of binary choice more accurately than bi- nary mean regression. In this paper, a credit assessment method of listed company in China is estab- lished via binary quantile regression approach. The performance of binary quantile regression model is compared with that of binary mean regression model through simulation study and real data analysis. The results indicate that the proposed method can more accurately evaluate the credit of listed compa- ny no matter in-sample or out-of-sample.