The Application Of Partially Linear Single-index Model In Stock Price Prediction

Partially linear single-index model(PLSIM) is a kind of semiparametric model ofcombine of linear model(LM) with single-index model(SIM). The model can chieve balancebetween paramteric statistical inference and nonparamteric statistical inference. Beacuse of itsadvantage, it is applied in the fields of economy, biology and medicine.With the development of chinese economy and investment market, more and morepeople pay great attention to the stock investment and participate in the stock market. Stockmarket play an important role in financial field of a country and the investors are the mostintrested in stock price. It is a difficult thing for investors to choose excellent stock becausestock market exist a lot of uncertain factors, and they long to know scientific analysis andprediction about stock price. At present, relevant researchers have obtained some effectivemethods by hard work to deal with above issue.In view of the advantage of PLSIM and the focus issue on stock price foreast, this thesisproceeds from the main financial indicators of the listed companies, and uses PLSIM toexplore the relationship between the stock price and financial index of the enterprises. Thepaper mainly devoted to the following aspects:Firstly, the thesis introduces the concept and basic knowledge related to stock, includemain feature, influencing factor, financial index and so on. It is helpful that introduce themain financial index which influences the stock price for applying the PLSIM. In addition,some foreasting methods about stock price are introduced, and the basic characteristic,advantages and disadvantages of the each method are described.Secondly, this paper introduces the development, general situation and the latest researchof the SIM and PLSIM are summarized, moreover, gives the estimators about unknownparameters and unknown function in the studied model.Thirdly, an empirical analysis of stock prices is carried out. It is through dimensionalityreduction to predict the relationship between the financial index and stock price fits thePLSIM. By compared predicted result with the LM show that PLSIM is better that than LM inthe prediction of stock price, so proposed method have application value in the stock market.