论文部分内容阅读
本文论证了双曲模型是描述中国货币市场利率动态变化的最佳单因子利率模型。由极大似然估计可以得到单因子利率模型的边际密度函数。双曲模型的边际密度和非参数估计得到的边际密度函数拟合较好,其表现远远优于几个常见的利率模型(CIR、CKLS和AG模型)。与较一般的At-Sahalia模型相比差别很小,但参数形式得到简化,似然比检验也支持这一点。双曲模型在刻画利率的均值回复特征方面还克服了AG模型的不足。
This paper demonstrates that the hyperbolic model is the best one-factor interest rate model that describes the dynamic changes in interest rates in the money market in China. The MLF of the single-factor interest rate model can be obtained from maximum likelihood estimation. The marginal density function of the hyperbolic model is better than the marginal density function obtained from the nonparametric estimation, which outperforms several common interest rate models (CIR, CKLS and AG models). Compared with the more general At-Sahalia model, the difference is very small, but the parameter form is simplified, and the likelihood ratio test supports this point. Hyperbolic model also overcomes the shortcomings of the AG model in describing the mean response characteristics of interest rates.