为改进传统Beta系数测量系统风险的不足,反映系统风险的动态特征,讨论了四阶矩的资本资产定价模型(CAPM)并将小波分析引入到高阶矩CAPM研究中。利用小波多分辨分析的特点,给出了小波高阶中心矩和高阶混合中心矩的定义,基于此给出了多分辨系统风险测度Beta、Gamma、Theta的计算方法和多分辨CAPM,并从行为金融理论出发,给出多分辨高阶矩CAPM的金融背景解释。实证结果支持了多分辨系统风险假说和多分辨高阶矩CAPM的成立,为构建动态投资组合分散金融风险的动态影响提供了证据。
To advance Betas for measuring systematic risk and reflect dynamic characteristic of the risk, the paper discusses four moments CAPM and wavelet analysis at the same time. Based on multi-resolution analysis, it puts forward the definitions of both wavelet high central moments and high mixed central moments. Further more, it also establishes the methods for calculating Betas, Gammas and Thetas and multi-resolution CAPM, and explains the financial background according to finance theory. The empirical results hold out the hypothesis of multi-resolution systematic risk and multi-resolution CAPM, which provide experienced evidence for dynamic portfolio to disperse risk.