Financial Crisis in the Logistic Regression Model’s Construction and Testing
|School||Qingdao Technological University|
|Keywords||Financial crisis Warning Regression model Listed companies|
Since 2007, the global economic crisis triggered by the U.S. subprime mortgage crisis spread further harm expanding overwhelmed many enterprises have been closed down. Increasingly become a national financial early warning issues, enterprises attach great importance to the problem. The purpose of this study is to analyze the various inspections and screening of the financial indicators of listed companies to find solutions that can significantly distinguish financial crisis, companies and non-financial crisis, the company's financial early warning indicators, and logistic regression model to establish financial early warning of China's listed companies model, the Greek help listed companies to detect and defuse the financial crisis, making it onto the track of normal development. Learn from the results of previous studies based on analytical methods, using a combination of normative and empirical research. Empirical research using the statistical software SPSS statistical software, the sample is divided into training and testing samples 465 manufacturing listed companies, the main contents are as follows: Chapter 1 Introduction. This chapter illustrates the research background and significance of the paper, the research methods and research ideas. Literature review in Chapter 2 of the financial crisis early warning function. A detailed review of the main research results of domestic and foreign scholars on the Enterprise Service warning research are discussed, and the meaning and function of the financial crisis early warning. Chapter 3 of the study sample, variables, and model choice. The period of the sample group and build a logistic regression model, selected according to certain criteria selection until 2008 since 2006, 76 of China's Shenzhen and Shanghai ST and non-ST-399 manufacturing enterprises, select 22 model of traditional financial indicators and six cash flow indicators. Finally, the comparison of the three important financial early warning model, we use the logistic model to establish financial early warning model. Chapter 4 the Logistic warning model and the applicability of test. The principal component analysis, non-parametric tests on the basis of financial indicators, gradually excluded variables other methods to select the model has a significant contribution to the financial indicators into the model were constructed in accordance with the three years before the financial crisis occurred at different ages three financial crisis early warning model. Finally, the selected sample test back-contracting. The results found that the financial crisis before the T-1, T-2, T-3 years of validation, respectively: 90.51%, 86.78%, 74.03%. This fully established the first three years of the three early-warning model achieved better forecast results have great practical value. Chapter V Conclusion. Come to the conclusion of this study, the research features and research prospects.