基于SARIMA模型的河北省居民人均消费性支出预测

Prediction of Per Capita Consumer Expenditure in Hebei Province Based on SARIMA Model

摘要: 本文基于2013年第1季度~2022年第3季度河北省居民消费性支出的季度数据，利用Rstudio软件进行分析，以2013第1季度~2021年第4季度的数据为训练集，以2022年的数据为测试集。原始序列为非平稳序列，1阶4步差分后，序列趋于平稳，故采用SARIMA加法模型进行预测，并根据AIC信息准则确定模型的拟合效果最优，且其预测结果通过了显著性检验，能够为各级政府提出平衡供需市场的策略提供一定的参考价值。

Abstract: Based on the quarterly data of consumer spending of residents in Hebei Province from the first quarter of 2013 to the third quarter of 2022, this paper uses Rstudio software for analysis, taking the data from the first quarter of 2013 to the fourth quarter of 2021 as the training set, and the data from 2022 as the test set. The original series is non-stationary, and the series tends to be stable after the first order four-step difference, so the SARIMA additive model is used for prediction, and the fitting effect of the model is determined to be the best according to AIC information criteria, and the prediction results have passed the significance test, which can provide a certain reference value for governments at all levels to propose strategies to balance the supply and demand market.