基于贝叶斯模型平均 (BMA) 方法的中国通货膨胀的建模及预测
Wei Chen and
Linlin Niu
No 2013-12-05, Working Papers from Wang Yanan Institute for Studies in Economics (WISE), Xiamen University
Abstract:
模型和参数的不确定性、以及信息的综合有效利用是影响宏观变量预测精度的主要因素。本文运用贝叶斯模型平均(BMA)方法建模并对样本外通胀进行预测,综合备选模型及变量的信息,以控制模型不确定性,并有效利用丰富的宏观数据信息。本文选取28个解释变量构建了含有2^28个单一线性模型的集合,实证上采用了马尔科夫链蒙特卡洛模型综合算法(MC^3)对备选模型进行抽签,抽签次数为1000万次。采用中国宏观数据的实证结果表明,通胀一阶滞后项与工业企业增加值增速作为预测因子几乎被选择在所有预测模型中;对于通胀的样本内拟合,贝叶斯模型平均(BMA)方法优于单一模型;对于样本外预测,在 标准下,贝叶斯模型平均方法的预测能力优于较为流行的 模型、主成分分析模型、菲利普斯曲线模型、利率期限结构模型、单一最优模型和五变量模型。
Keywords: 贝叶斯模型平均;通货膨胀;蒙特卡洛模拟;MC^3 (search for similar items in EconPapers)
JEL-codes: C11 E31 E47 (search for similar items in EconPapers)
Date: 2013-12-05
References: Add references at CitEc
Citations:
Published
Downloads: (external link)
https://econpub.xmu.edu.cn/research/repec/upload/201312051550323142.pdf (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:wyi:wpaper:002207
Access Statistics for this paper
More papers in Working Papers from Wang Yanan Institute for Studies in Economics (WISE), Xiamen University
Bibliographic data for series maintained by WISE Technical Team ().