系统抽样、脉冲响应与通货膨胀惯性

Systematic Sampling,Impulse Response and the Persistence of Inflation

利用时间序列模型研究经济变量的动态特征时,模型估计结果通常随样本观测频率改变而变化。本文针对系统抽样问题,研究样本观测频率变化对脉冲响应函数和累积脉冲响应的影响,探讨不同观测频率下脉冲响应函数的理论联系,以及对变量持久性特征更加稳健的度量方法,在此基础上考察中国通货膨胀的动态特征。结果表明,累积脉冲响应和惯性系数随样本观测频率提高而增加;系统抽样对脉冲响应函数的影响源于外生冲击界定的不同,脉冲响应的数值意义有限,但可用其考察冲击影响的持续时间;外生冲击对中国通货膨胀的影响持续2年左右,且90%在1年内实现,央行要对通货膨胀走势有很强的预判能力,政策滞后将增加反通货膨胀成本。

In the study about the dynamic characteristics of economic variables using time series model, the estimation results will vary with the frequency of observation. In this paper, we study the influence of systematic sampling on impulse response function （IRF） and cumulative impulse response （CIF）, to explore the relationship between IRFs of different observation frequency, and more robust measure of the persistence of economic variables. Based on the above, the dynamic characteristics of Chinese inflation are investigated. The result shows that, CIF and inertial coefficient usually increase with sample observation frequency increasing ; the effect of temporal aggregation on IRF stems from the different definition of exogenous shock, which means that the economic implication of IRF＇ s numerical value is limited, but the duration of the response to a shock can be examined by IRF; The response of Chinese inflation to exogenous shock lasts about 2 years, and 90% of them is achieved within I year. Therefore, the central bank should have strong ability to predict the future inflation trend, and implement monetary policy without delay to reduce the cost of disinflation.