| 基于最优非负可变加权系数组合预测法的CPI预测研究 |
| |
| 引用本文： | 邹建岚,曾智.基于最优非负可变加权系数组合预测法的CPI预测研究[J].福建教育学院学报,2013(6):113-116. |
| |
| 作者姓名： | 邹建岚 曾智 |
| |
| 作者单位： | [1]福建工程学院,福建福州350108 [2]兴业国际信托有限公司,中国上海200120 |
| |
| 摘 要： | 准确的物价预测是稳定物价的前提之一,及时根据预测结果制定有针对性的宏观经济措施,对维持经济系统的有效运行、保证居民的生活稳定有着重要的意义.文章分别采用回归预测法、ARMA时间序列预测法、VAR模型预测法和BP神经网络预测法四种单项预测方法和最优非负可变加权系数组合预测法对我国物价走势进行预测,并将预测值进行对比分析,得出最优非负可变加权系数组合预测方法能够综合各单项预测方法的信息,有效提高预测精度,该模型可以用作我国物价走势预测的模型的结论.
|
| 关 键 词： | CPI预测 组合预测法 宏观调控 加权系数 |
Research Based on the Optimal Non-negative Variable Weighting Coefficient Method of the CPI Prediction |
| |
| ZOU Jian-lan,ZENG Zhi.Research Based on the Optimal Non-negative Variable Weighting Coefficient Method of the CPI Prediction[J].Journal of Fujian Education Institute,2013(6):113-116. |
| |
| Authors: | ZOU Jian-lan ZENG Zhi |
| |
| Institution: | 2 (1. Fujian University of Technology, Fuzhou 350108, China： 2. China Industrial International Trust Limited, Shanghai 200120, China) |
| |
| Abstract: | An accurate price forecast is one of the prerequisites in price stability. It is of great significance to take timely some macroeeonomic measures according to the results of the forecast, for it will maintain the effective functioning of the economic system and ensure the stability of life of the residents. This paper uses the regression method, ARMA time series prediction method, VAR model prediction method and BP neural network forecasting method, the four kinds of individual prediction methods and the optimal non-negative variable weighting coefficient of combination forecasting method to predict price trends, analyzes forecasts values and come to the conclusion that the optimal combination of non-negative variable weighting coefficient prediction method is able to integrate the in- dividual prediction methods, effectively improve the prediction accuracy of the model and can be used as a model for forecasting price trends in China. |
| |
| Keywords: | CPI forecast combination forecasting method macro adjustment weighting factor |
| 本文献已被 维普 等数据库收录！ |
|
