The Empirical Research On Influence Factor And Forecast Model Of Financial Crisis Of The Listed Companies In China

With the quick development of capital market, the complexity and uncertainty in economic field becomes increasingly evident, and it comes to be widespread that financial crisis and bankruptcy occurs in enterprises more and more. Financial crisis not only menaces enterprises' subsistence and development but also influences the benefits of the investors, the creditors, and the state. Therefore, the research on effect factor and forecasting model of financial crisis happening is absolutely necessary.With the sign whether the corporation is "special treated" or not, the thesis, basing on existing researches, selects the initial samples which are composed of 80 ST firms and 80 non-ST firms in two groups, besides, selects six non-financial data for supplementary and contradistinctive research. Firstly, the text discusses the data relativity and the differences of variables between the two groups up to T-2 and T-3 year prior to the failure event. Then the study uses Factor Analysis to reduce data and filter data as independent variable of model. Finally, the text uses COX model which is popular in Medical Research to analyze key influence factors for financial crisis, then, uses Logistic Regression Model to establish forecasting model and tests 80 firms of the holdout samples to estimate forecast rate.The dissertation comes into conclusion in the end: firstly, COX Factor Analysis Model can differentiate protecting factors and danger factors which influence financial crisis. The text reveals that some factors have a positive effect on financial crisis and others have a negative effect. Secondly, financial data of corporation is not perfect, but the data still contains some certain information. Meanwhile, non-financial data is a good supplementary for financial data and reduce wrong information of financial statement. It depicts that non-financial index is very useful for forecast research of financial crisis.