云南省财政预算收支关系及预测研究

Research on the Relationship between Revenue and Expenditure of Fiscal Budget in Yunnan Province and Its Forecast

摘要: 本文基于1991~2021年云南省财政预算收支年度数据，采用Rstudio软件进行分析，对财政收入和财政支出序列进行二阶差分后得到两个平稳非随机时间序列，通过协整检验发现云南省财政收入和财政支出存在长期均衡关系，而ECM模型则显示其短期波动影响不显著，Granger因果关系检验结果显示财政支出是财政收入的格兰杰原因。接着通过模型的识别和定阶，比较AIC信息准则分别拟合最优的云南省财政预算收入的ARIMA模型，得到的最优财政预算收入模型ARIMA(1，2，0)，同时使用2015~2021年的云南省财政预算收入数据真实值与模型拟合值进行比较，得出模型拟合平均误差率为2.9588%，认为模型的短期预测效果较为理想。最后使用该模型对云南省2022~2029年财政预算收入进行预测，预测结果可为财政预算编制提供参考。

Abstract: Based on the annual data of fiscal budget revenue and expenditure of Yunnan Province from 1991 to 2021, this paper uses Rstudio software to analyze, and obtains two stationary non-random time series after the second-order difference of fiscal revenue and fiscal expenditure series. Through the cointegration test, it is found that there is a long-term equilibrium relationship between fiscal rev-enue and fiscal expenditure of Yunnan Province, while the ECM model shows that its short- term fluctuation has no significant impact, Granger causality test results show that fiscal expenditure is the Granger cause of fiscal revenue. Then through the identification and ranking of the model, com-pare the ARIMA model of the best fiscal budget revenue of Yunnan Province fitted by AIC infor-mation criteria, and get the best fiscal budget revenue model ARIMA(1, 2, 0). At the same time, compare the real value of the fiscal budget revenue data of Yunnan Province from 2015 to 2021 with the model fitting value, and get the average error rate of the model fitting is 2.9588%, and think that the short-term prediction effect of the model is ideal. Finally, the model is used to fore-cast the fiscal budget revenue of Yunnan Province from 2022 to 2029, and the forecast results can provide a reference for fiscal budget preparation.