摘要
Accurately predicting stock returns is a conundrum in financial market.Solving this conundrum can bring huge economic benefits for investors and also attract the attention of all circles of people.In this paper the authors combine semi-varying coefficient model with technical analysis and statistical learning,and propose semi-varying coefficient panel data model with individual effects to explore the dynamic relations between the stock returns from five companies:CVX,DFS,EMN,LYB,and MET and five technical indicators:CCI,EMV,MOM,ln ATR,ln RSI as well as closing price(ln CP),combine semi-parametric fixed effects estimator,semi-parametric random effects estimator with the testing procedure to distinguish fixed effects(FE) from random effects(RE),and finally apply the estimated dynamic relations and the testing set to predict stock returns in December 2020 for the five companies.The proposed method can accommodate the varying relationship and the interactive relationship between the different technical indicators,and further enhance the prediction accuracy to stock returns.
基金
supported by the Natural Science Foundation of CQ CSTC under Grant No.cstc.2018jcyj A2073
Chongqing Social Science Plan Project under Grant No.2019WT59
Science and Technology Research Program of Chongqing Education Commission under Grant No.KJZD-M202100801
Mathematic and Statistics Team from Chongqing Technology and Business University under Grant No.ZDPTTD201906
Open Project from Chongqing Key Laboratory of Social Economy and Applied Statistics under Grant No.KFJJ2022056
Chongqing Graduate Research Innovation Project under Grant No.CYS23568。
