404 Not Found

404 Not Found


nginx
返回首页
半非参数模型选择研究以及在上交所回购利率中的应用

作者:肖 永

2013-05-14 09:38:34 来源:数量经济技术经济研究

上海财经大学金融学院 200433

 

 

基于“模型动态稳定性”要求,本文改进了半非参数SNP)模型的选择方法,使所选择的SNP模型既能很好地拟合真实样本又能模拟出与真实样本统计特征相近的时间序列。其次,本文得到了二维随机过程情形下赫米特展开项的理论结果。第三,实证结果表明:上交所旧质押式回购利率初始、插值后样本两组数据的最优SNP模型均为Semiparametric AR(1)-GARCH(1,1)(即11118000)模型,但是两者的系数估计值却不相同。最后,本文的实证结果既反映了上交所回购利率存在均值回复、条件异方差性和波动率聚集等特征,又证实了本文所提出的SNP模型选择改进方法的合理性与稳定性。

关键词:半非参数模型、模型动态稳定性、向上扩展路径方法

 

Research on Seminonparametric Model Selection with Application to the Pledged Repo Interest Rate in Shanghai Stock Exchange

Xiao   Yong

Schoolf of Finance, Shanghai University of Finance and Economics, 200433

Abstract

Based on model dynamic stability, to begin with, this article improves the approach of selecting SNP (Seminonparametric) model, making the SNP model selected better can appropriately fit the true sample and simulate a time series with statistical property similar to the true sample. Secondly, I derive theoretical result for the Hermite expansion terms under 2-dimensional stochastic processes. Thirdly, I empirically show that the optimal SNP model, for both raw data and interpolated data of pledged repo interest rate in the Shanghai Stock Exchange, is coincidently the Semiparametric AR(1)-GARCH(1,1) model, the 11118000 model, except for different parameter estimates. Finally, my empirical results illustrate that the repo interest rate can be characterized by mean reversion, conditional hetroskedasicity and volatility clustering etc., and prove that the way to improve SNP model selection is appropriate and stable.

 

Key Words: Seminonparametric Model, Model Dynamic Stability, Upward Expansion Path


一、引言

对于平稳时间序列而言,其单步转移密度函数(简称转移密度或条件密度)可以完全描述所有的统计信息。因此,如果假定某些金融时间序列(例如短期利率过程)满足平稳性条件,则只需考察其条件密度函数。Philips1983)采用半非参数(Seminonparametric,简称SNP)方法对平稳过程的条件密度函数进行了研究;Gallant and Nychka1987)对其进行了拓展;Gallant and Tauchen1989)将由SNP方法得到的条件密度函数应用于资产定价领域。Gallant and Tauchen1996)认为,和广义矩估计方法(GMM)相比,有效矩估计方法(EMM[1]所选择的矩条件通常更加“有效”,这归结于得分函数(score function)在矩条件中所起的重要作用。而得分函数的确定则完全取决于半非参数条件密度函数(也称为半非参数模型或SNP模型)。

半非参数方法的实质是采用赫米特(Hermite)函数对真实条件密度函数进行序列展开,从而得到真实条件密度函数的估计量。因此,本文首先得到了二维随机过程情形下SNP模型中赫米特高阶展开项的具体结果。



[1] EMMGMM分别为efficient method of momentsgeneralized method of momentsHansen,1982)缩写。

 

 

 

 

404 Not Found

404 Not Found


nginx