时变三因子模型风险系数的动态研究

Study on Risk Coefficient of Time-varying Three-factor Model

由Fama和French提出的三因子模型能够较好地解释股票的收益率风险溢价。文章以状态空间模型为框架,将风险因子系数作为状态变量,市场风险溢价作为观测变量,构建时变三因子模型来应对股票市场价格的时变特征。研究结果显示,利用卡尔曼滤波来估计时变风险因子系数,增强了估计结果的准确性与连贯性;风险因子系数变化规律与中国A股市场政策和环境影响相吻合,消除非理性噪声后的时变三因子模型更具有解释力度。

The three-factor model proposed by Fama and French can better explain the return risk premium of stocks.This paper takes the state space model as the framework,the risk factor coefficient as the state variable and the market risk premium as the observation variable,and constructs a time-varying three-factor model to deal with the time-varying characteristics of stock market prices.The results show that using Kalman filter to estimate the time-varying risk factor coefficient enhances the accuracy and consistency of the estimation results;the variation rule of risk factor coefficient is consistent with the policy and environmental impact of China’s A-share market,and the time-varying three-factor model after eliminating irrational noise has more explanatory power.