引用本文:周亮.基于分位数回归的多因子选股策略研究[J].西南大学学报(自然科学版),2019,41(1):89~96
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 242次   下载 138 本文二维码信息
码上扫一扫!
分享到: 微信 更多
基于分位数回归的多因子选股策略研究
周亮
湖南财政经济学院 学报编辑部, 长沙 410205
摘要:
选取2007年初至2017年末的中证500指数成分股规模、股价、市盈率、动量、换手率和波动率6个因子的所有年度数据,探讨了分位数回归在多因子选股策略中的应用情况.结果表明:对于单因子而言,规模因子和股价因子均在高收益率股票中表现出更强的效应,市净率、动量及换手率因子均在低收益率股票中表现出更强的效应,波动率因子则在高收益率股票和低收益率股票中均表现出较强的效应;多因子选股模型均表现出优于OLS回归模型的投资效果,规模-股价模型在样本区间可以获得43.17%的年化收益率,而市净率-动量-换手率因子选股模型可以获得18.48%的年化收益率.
关键词:  分位数回归  多因子  选股策略
DOI:10.13718/j.cnki.xdzk.2019.01.014
分类号:F830.91
基金项目:国家社会科学基金项目(14BJL086);湖南省教育厅科学研究项目(14B031).
Multi-Factor Strategy Based on Quantile Regression
ZHOU Liang
Editorial Department, Hunan University of Finance and Economics, Changsha 410205, China
Abstract:
This paper selects all the annual data of six factors including the size, stock price, price-earnings ratio, momentum, turnover rate and volatility of the CSI 500 Index from the beginning of 2007 to the end of 2017, and explores the application of quantile regression in multi-factor stock selection strategy. The results show that:for the single factor, both the size factor and the stock price factor show stronger effects in the high-yield stocks; and the market-to-net ratio, momentum and turnover factor all show stronger effect in the low-yield stocks; the volatility factor in the high yield and low yield stocks have shown strong effects; multi-factor stock selection models have shown better than the OLS regression model of investment results, scale-stock price model can obtain 43.17% of the annualized yield in the sample interval, while the PBR-Momentum-turnover ratio factor stock selection model can get an annualized yield of 18.48%.
Key words:  quantile regression  multi-factor  stock selection strategy
手机扫一扫看