A penalized U-MIDAS multinomial logit model with applications to corporate credit ratings

IF 3.8 3区经济学 Q1 BUSINESS, FINANCE

North American Journal of Economics and Finance Pub Date : 2025-01-01 DOI:10.1016/j.najef.2025.102381

Cuixia Jiang , Junwei Sun , Qifa Xu

引用次数: 0

Abstract

We develop a penalized U-MIDAS-Mlogit model by introducing the group LASSO penalty into the unrestricted MIDAS multinomial logit model. This penalized U-MIDAS-Mlogit model can implement multinomial classification in a high-dimensional mixed-frequency data environment. We apply it to credit ratings for listed companies in China over the period 2008–2023. The penalized U-MIDAS-Mlogit model can extract pivotal information from high-frequency financial variables and low-frequency internal and external governance indicators. It outperforms several competing models in predicting credit ratings.

查看原文本刊更多论文

一个被惩罚的U-MIDAS多项逻辑模型及其在企业信用评级中的应用

通过在无限制MIDAS多项logit模型中引入组LASSO惩罚，建立了受惩罚的U-MIDAS-Mlogit模型。该惩罚型U-MIDAS-Mlogit模型可以在高维混频数据环境下实现多项分类。我们将其应用于2008-2023年间中国上市公司的信用评级。受到惩罚的U-MIDAS-Mlogit模型可以从高频财务变量和低频内部和外部治理指标中提取关键信息。它在预测信用评级方面优于几个竞争模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

North American Journal of Economics and Finance Multiple-

CiteScore

7.30

自引率

8.30%

发文量

168

期刊介绍： The focus of the North-American Journal of Economics and Finance is on the economics of integration of goods, services, financial markets, at both regional and global levels with the role of economic policy in that process playing an important role. Both theoretical and empirical papers are welcome. Empirical and policy-related papers that rely on data and the experiences of countries outside North America are also welcome. Papers should offer concrete lessons about the ongoing process of globalization, or policy implications about how governments, domestic or international institutions, can improve the coordination of their activities. Empirical analysis should be capable of replication. Authors of accepted papers will be encouraged to supply data and computer programs.