我国费雪效应的非参数检验

Nonparametric Test of Fisher Effect in China

本文基于我国1990:01—2007:04期间的名义利率与通货膨胀率月度数据非线性变化的特征,应用非参数单位根和非参数协整理论检验我国是否存在费雪效应,进而应用非参数局部线性变窗宽估计计算我国的费雪系数。由此产生的结论为:第一,非参数单位根检验发现我国名义利率与通货膨胀率都是非平稳的单位根过程;第二,非参数协整检验的结论为,我国名义利率与通胀变化率之间存在长期的非线性协整关系,这一结论表明我国至少存在弱的费雪效应;第三,非参数局部线性变窗宽估计计算的费雪效应(系数)的均值为0.4055,这一结果进一步支持我国存在弱的费雪效应,其隐含的意义为,当前加息对稳定通胀将产生正面效应,进一步,如适时适度的调整利率,很可能抑制当前较高的CPI向高通胀的转化。

Based on the nonlinear change characteristics of the nominal interest rate and inflation rate in China,this paper tests Fisher Effect by nonparametric unit roots and nonparametric cointegration test.Moreover,we estimate the Fisher effect coefficients by nonparametric local linear estimation with variant bandwidth（LLEVB）.The conclusion are as follows： Firstly,we find that both the nominal interests rate and inflation rate are nonstationary unit roots process by nonparametric unit roots test.Secondly,nonparametric cointegration test concludes that there is an unknown nonlinear cointegration relation between the nominal interest rate and inflation rate which implies there exists weak Fisher Effect.Thirdly,the averaged Fisher Coefficient is 0.4055 by LLVEB,this result shows that there exists weak Fisher Effect once again.The potential meaning of the conclusions is that Chinese monetary policy should change to mainly implement the tool of interest rate.