全国人口时间序列模型预测研究

Study on population projection in China based on time series model

对1949—2010年全国人口时间序列数据进行了分析,并建立自回归移动平均模型(ARIMA).通过对数据的平稳性检验、模型识别与参数估计、模型检验等综合分析,确立了ARIMA(2,1,1)模型.仿真结果显示,该模型可以用来做短期预测.

Analyzed tile time series of population in China from1949 to 2010, constructed the ARIMA model. Through analyzing the data of stationary test, model identification, parameter estimation and model checking, the ARIMA（2,1,1） model was established. The results showed that the forecast of this model is more exact and precise for a short-term prediction of the time series of population in China.