基于ARMA模型的四川省农村居民收入趋势预测.PDFVIP

中国农学通报 2012,28(05): 110-114 Chinese Agricultural Science Bulletin 基于ARMA 模型的四川省农村居民收入趋势预测 卢小丽，何 光 （内江师范学院，四川内江641100） 摘 要：基于1978—2010 年四川省农村居民人均纯收入的时间序列，先后通过平稳化检验及处理、自相 关与偏相关分析，并结合SC 准则定阶，建立模型为ARMA(5,5) ；然后确定模型参数并对模型的残差序 列进行白噪声检验，检验通过，满足预测的要求；运用该模型对四川省农村居民人均纯收入进行预测，结 果显示平均绝对误差率为1.81% ，其中2010 年误差率为1.21% ，精度较高；最后对2011—2013 年进行短 期预测，数据表明，农村居民人均收入将继续增长，但增长幅度呈下降趋势。 关键词：ARMA 模型；农村居民收入；时间序列；预测 中图分类号：F32 文献标志码：A 论文编号：2011-2252 The Forecasting Trend of Rural Residents Income in Sichuan Province Based on ARMA Model Lu Xiaoli, He Guang (Neijiang Normal University, Neijiang Sichuan 641100) Abstract: Based on the time series of rural residents per net income in Sichuan Province from 1978 to 2010, through stationary test and disposal, auto correlation and partial correlation analysis, and combing SC criterion, the model of ARMA (5,5) was established. After model parameters were estimated, white noise test about residual series of the model was done. It was showed that results pass test and meet forecast demand. Then rural residents per net incomes in Sichuan Province were estimated with the model, and mean absolute per error was 1.81%, error ratio in 2010 was 1.21%, therefore the precision was higher. Finally rural residents per net incomes in 2011 to 2013 were forecasted, it was demonstrated that the incomes would kept on rise and the increase range was downtrend. Key words: ARMA model; rural residents income; time series; forecast 0 引言 偏向于分析城乡居民收入差异的变化趋势，对农村居 2010 年农业部提出“千方百计保持农民收入增长 民收入进行预测的研究并不多。 6 ％以上”的号召，以农民为主的农村居民收入问题引