云南省总人口预测模型的比较研究

楚雄师范学院学报 ›› 2021, Vol. 36 ›› Issue (3): 8-15.

云南省总人口预测模型的比较研究

郭靖^*, 张银香

云南师范大学数学学院,云南昆明 650500

收稿日期:2020-07-23 出版日期:2021-05-20 发布日期:2021-07-23
作者简介:郭靖（1995–）,男,硕士研究生,主要研究方向为生物医学统计。E-mail： 2541631370@qq.com ,Tel. 18487730218

Application and Comparison of ARIMA Model and Holt Two Parameter Model in Population Forecast

GUO Jing, ZHANG Yinxiang

College of Mathematics, Yunnan Normal University, Kunming, Yunnan Province 650500

Received:2020-07-23 Online:2021-05-20 Published:2021-07-23

摘要/Abstract

摘要： 本文以1973~2018年云南省总人口为例,分别建立Holt两参数指数平滑模型、ARIMA模型和三次多项式模型,利用最小AIC准则从ARIMA模型中选出了ARIMA（4,3,1）模型,与Holt两参数指数平滑模型和三次多项式模型做比较。通过模型预测值的平均误差率和残差的波动幅度的比较后,发现ARIMA（4,3,1）模型的拟合精度较高,适合用来预测短期的总人口数。基于此分析对云南省总人口进行了8期数的预测,发现云南省总人口数量呈现不断增加的趋势,但总人口数增长速率下降,总人口数量趋向饱和状态。

关键词: ARIMA模型（Autoregressive integrated moving average model）, Holt两参数指数平滑模型, 三次多项式模型, 人口预测, 模型比较

Abstract: Taking the total population of Yunnan Province from 1973 to 2018 as an example, this paper establishes the Holt two-parameter exponential smoothing model, the ARIMA model and the cubic polynomial model. The ARIMA (4,3,1) model is selected from the ARIMA model using the minimum AIC criterion and is compared with Holt's two-parameter exponential smoothing model and cubic polynomial model. After comparing the average error rate of the predicted value of the model with the fluctuation range of the residual, the ARIMA(4,3,1) model has a higher fitting accuracy and is suitable for predicting the total population in the short term. Based on this analysis, the total population of Yunnan Province was predicted for 8 periods.

Key words: ARIMA model, Holt two-parameter exponential smoothing model, cubic polynomial model, population forecasting, model comparison

中图分类号:

C924.257.4

郭靖, 张银香. 云南省总人口预测模型的比较研究[J]. 楚雄师范学院学报, 2021, 36(3): 8-15.

GUO Jing, ZHANG Yinxiang. Application and Comparison of ARIMA Model and Holt Two Parameter Model in Population Forecast[J]. Journal of Chuxiong Normal University, 2021, 36(3): 8-15.

参考文献

[1] 顾翠伶,王宁. ARIMA模型在人口序列预测中的应用[J].周口师范学院学报,2016,33(5):50–52.
Gu C L, Wang N.ARIMA model application in prediction of population[J]. Journal of Zhoukou Normal University, 2016, 33(5): 50–52.
[2] 李志超,刘升.基于ARIMA模型、灰色模型和回归模型的预测比较[J].统计与决策,2019,35(23):38–41.
Li Z C, Liu S.Prediction comparison based on ARIMA model, Grey model and Regression model[J]. Statistics & Decision, 2019, 35(23): 38–41.
[3] 陈艳玫,刘子锋,李贤德,等.2015~2050年中国人口老龄化趋势与老年人口预测[J].中国社会医学杂志,2018, 35(5): 480–483.
Chen Y M, Liu Z F, Li X D,et al. The aging trend of Chinese population and the prediction of aging population in 2015–2050[J]. Chinese Journal of Social Medicine, 2018, 35(5):480–483.
[4] Zakria M, Muhammad F.Forecasting the population of Pakistan using ARIMA models[J]. Pakistan Journal of Agricultural Sciences,2009,46(3): 214–223.
[5] Mishra A K, Sahanaa C, Manikandan M.Forecasting Indian infant mortality rate: An application of autoregressive integrated moving average model[J]. Journal of Family & Community Medicine, 2019,26(2): 123–126.
[6] 王艳. 时间序列分析—基于R[M].北京:人民大学出版社,2015:119–120.
Wang Y.Time Sseries Analysis With R [M]. Beijing: China Renmin University Press, 2015: 119–120.
[7] 罗佳沩. 基于回归模型的全国人口预测研究[J].黑龙江科学,2019,10(18):146–148.
Luo J W.Research on national population forecast based on regression model[J]. Heilongjiang Science, 2019,10(18): 146–148.
[8] 苏理云,殷勇,李晨龙.应用多项式系数统计模型的人口预测[J].重庆理工大学学报(自然科学), 2014,28(4): 138–142.
Su L Y,Yin Y,Li C L.Population prediction based on polynomial coefficient statistical model[J]. Journal of Chongqing University of Technology (Natural Science), 2014,28(4): 138–142.
[9] 贾洪文,谢卓军,高一公.甘肃省人口预测与发展趋势分析[J].西北人口,2018,39(3):118–126.
Jia H W,Xie Z J,Gao Y G.Population forecast and development trend in Gansu province[J]. Northwest Population Journal, 2018,39(3):118–126.
[10] 孙双琳,冉凤.人口模型在贵州省总人口预测中的应用[J]. 贵州工程应用技术学院学报,2014,32(8):24–31.
Sun S L, Ran F.The application of demographic models for population forecast of Guizhou province[J]. Journal of Guizhou University of Engineering Science, 2014,32(8): 24–31.
[11] 刘锋,何卓,谭祥勇.Richards模型与Logistic模型在人口预测中的比较[J].重庆工商大学学报(自然科学版),2017,34(1):6–9.
Liu F, He Z, Tan X Y.Comparison of Richards model and Logistic model in population prediction[J]. Journal of Chongqing Technology and Business University(Natural Science Edition), 2017,34(1): 6–9.
[12] Francis L, Vicent K.A comparative analysis of the application of seasonal ARIMA and exponential smoothing methods in short run forecasting tourist arrivals in Tanzania[J]. European Journal of Business and Management, 2017, 9(10): 56–69.
[13] 杨世娟,李胜.安徽省人口发展趋势预测—单一模型与组合模型的模拟仿真比较[J].黄山学院学报, 2017,19(5): 1–5.
Yang S J, Li S.The prediction of population development trend in Anhui province-a comparison of the single models and combined model[J]. Journal of Huangshan University, 2017, 19(5): 1–5.
[14] Guo F F, Xiang R J, Li L P.Application of GM (1, 1) and seasonal cross-trend model in the forecast of tourist population in Sanya[J]. International Journal of Applied Evolutionary Computation, 2019, 10(4): 51–64.
[15] Hong G, Tian X Y, Xiao R K.Population forecast of Anhui province based on the GM(1,1) model[J]. Grey Systems: Theory and Application, 2017, 7(1): 19–30.