Construction of the Logistic Regression Estimation Model in Early Warning on Pure Financial Indicators

ABSTRACT

In order to establish a reasonable and effective financial crisis early warning model, the article chooses some financial indicators and uses factor analysis to get the common factors to conduct the most salient financial indicators. In the case that multirole linearity is not significant, the article uses the logistic regression to analyse eligible financial data and obtains the financial crisis warning model. Then the article found that this model has a high predictive accuracy.

Keywords:

Logistic regression estimation, factor analysis, early warning, financial indicators, experimental analysis.