An Empirical Study On Prediction Of Financial Distress In China's Listed Companies

In recent years, many listed companies run into financial distress frequently in China,coursing great damages to investors and creditors, and dampening security market'sdevelopment. So, it is necessary to do some predictive studies on financial distress.This paper takes China's manufacturing industry as sample. We match each STcompany with one financially healthy company of equal size, and select 218companies in total. First, we use t-test to compare financial indexes between healthycompanies and distress companies before they go distress, and find some significantvariables. In order to avoid the multicollineadty, we omit variables with largecorrelation coefficient, and 18 variables remain, which are basic variables to predict.After these, Single Variable Discriminant (SVD), Multivariable Discriminant Analysis(MDA), and Multivariable Logistic Analysis (MLA) are used to predict theprobability of financial distress of listed companies in this paper. Research shows thatthe MLA's correct percent of prediction is the highest among three methods givenabove. Finally, we study the differences between two type companies in the corporategovernance point of view. So certain ownership structure variables are designed andused in prediction models, these variables are helpful to improve these models'effectiveness.