Nelson-Siegel model （ NS model） and 2 extended NS models were compared by using daily interbank government bond data Based on the grouping of bonds according to the residual term to maturity, the empirical research ...Nelson-Siegel model （ NS model） and 2 extended NS models were compared by using daily interbank government bond data Based on the grouping of bonds according to the residual term to maturity, the empirical research proceeded with in-sample and outof-sample tests. The results show that the 3 models are almost equivalent in estimating interbank term structure of interest rates. Within the term to maturities between 0 and 7 years, the gap of the absolute errors of the 3 models between in-sample and out-of-sample is smRller than 0.2 Yuan, and the absolute values of the in-sample and out-of-sample errors are smaller than 0. 1 Yuan, so the estimation is credible. Within the term to maturities between 7 and 20 years, the gap of the absolute errors of the 3 models between in-sample and out-of-sample is larger than 0.4 Yuan, and the absolute values of the in-sample and out-of-sample errors are larger than 1.0 Yuan, so the estimation is incredible.展开更多
国债利率期限结构是固定收益产品定价和投资组合管理的核心问题。本文利用NARX(Nonlinear AutoRegressive network with e Xogenous inputs)神经网络模型研究利率曲线的运动机制,拟合并预测利率期限结构,在此基础上利用Hermite插值方法...国债利率期限结构是固定收益产品定价和投资组合管理的核心问题。本文利用NARX(Nonlinear AutoRegressive network with e Xogenous inputs)神经网络模型研究利率曲线的运动机制,拟合并预测利率期限结构,在此基础上利用Hermite插值方法构造平滑的利率曲线并计算得到国债理论价格及其预测值。实证分析发现:我国国债定价效率不足,交易价格显著偏离理论价格,但国债理论价格的实际值和预测值均对交易价格具有显著的预测能力。基于上述发现,本文提出了主动国债组合管理策略,通过预测的期限结构得到国债理论价格的预测值构建的多空对冲组合和单边多头组合均能获得显著的收益。展开更多
文摘Nelson-Siegel model （ NS model） and 2 extended NS models were compared by using daily interbank government bond data Based on the grouping of bonds according to the residual term to maturity, the empirical research proceeded with in-sample and outof-sample tests. The results show that the 3 models are almost equivalent in estimating interbank term structure of interest rates. Within the term to maturities between 0 and 7 years, the gap of the absolute errors of the 3 models between in-sample and out-of-sample is smRller than 0.2 Yuan, and the absolute values of the in-sample and out-of-sample errors are smaller than 0. 1 Yuan, so the estimation is credible. Within the term to maturities between 7 and 20 years, the gap of the absolute errors of the 3 models between in-sample and out-of-sample is larger than 0.4 Yuan, and the absolute values of the in-sample and out-of-sample errors are larger than 1.0 Yuan, so the estimation is incredible.
文摘国债利率期限结构是固定收益产品定价和投资组合管理的核心问题。本文利用NARX(Nonlinear AutoRegressive network with e Xogenous inputs)神经网络模型研究利率曲线的运动机制,拟合并预测利率期限结构,在此基础上利用Hermite插值方法构造平滑的利率曲线并计算得到国债理论价格及其预测值。实证分析发现:我国国债定价效率不足,交易价格显著偏离理论价格,但国债理论价格的实际值和预测值均对交易价格具有显著的预测能力。基于上述发现,本文提出了主动国债组合管理策略,通过预测的期限结构得到国债理论价格的预测值构建的多空对冲组合和单边多头组合均能获得显著的收益。
