桂林市汽车销售量的时间序列预测模型

The Forecasting Model of Time Series for the Auto Sales in Guilin

选取1999年1月到2007年3月桂林市各季度的汽车销售量原始数据,在SPSS系统下,运用滑动求和自回归(ARIMA)方法及非参数方法建立桂林市汽车销售量时间序列模型ARIMA(p,d,q),从模型识别、参数估计、适应性检验和实际拟合4个方面来确定模型的参数(p,d,q),并对模型的预测效果进行检验。结果表明,ARIMA(0,2,2)模型能够较好地包含桂林市汽车销售量的发展趋势,该模型对2007年2季度至2008年2季度汽车销售量的预测值与实际值的误差小,相对误差可以控制在3%以内。

Under the SPSS system, this paper carries out the analysis by useing the data of the auto sales in Guilin from January 1999 to March 2007, to confirm the time series model that mostly fit in with the development rule of the auto sales in Guilin from four aspects：model identification, parameter estimation, diagnostic checking and actual fitting. The research presents the auto sales from the second quarter in 2007 to the second quarter in 2008, compared with the actual value, the comparative error of the forecast value of the ARIMA （0,2,2） model is less than the 3 %. Therefore, the ARIMA（0,2,2） model fits the development rules of the auto sales in Guilin.