摘要
财政收入是国家对经济实行宏观调控的重要经济杠杆,准确预测财政收入对其意义重大,而ARIMA模型是短期预测财政收入的有效工具。以1950~2016年财政收入为样本,建立多组ARIMA模型,进而运多重筛选准则,找到最优滞后阶数p和q,最后确定了最优ARIMA(3,2,8)模型。该模型通过了多项假设检验,对2017~2018年的财政收入进行预测,结论表明预测精度高。同时也利用该模型对2019~2022年的财政收入进行了预测,为国家及政府提供一定的参考价值。
Fiscal revenue is an important economic lever for the state to implement macroeconomic regulation and control. Accurately predicting fiscal revenue is of great significance to it, and the ARIMA model is an effective tool for short-term forecasting of fiscal revenue. Taking the 1950~2016 fiscal revenue as a sample, multiple sets of ARIMA models were established, and then multiple screening criteria were applied to find the optimal lag order p and q. Finally, the optimal ARIMA(3,2,8) model was determined. The model has passed a number of hypothesis tests to predict the fiscal revenue of 2017~2018, and the conclusions indicate that the prediction accuracy is high. At the same time, this model is also used to forecast the fiscal revenue of 2019~2022 in the next few years, providing certain reference value for the country and the government.
出处
《应用数学进展》
2020年第3期414-420,共7页
Advances in Applied Mathematics
基金
辽宁省自然科学基金指导计划项目(编号:2019-ZD-0471)。
