摘要
未来物价预期指数是指居民对下季物价判断的扩散指数。文章运用从2009年第一季度到2018年第一季度共计37个季度的城镇居民有关数据,构建了以未来物价预期指数为被解释变量,当期收入感受指数等15个指标为解释变量的岭回归、Lasso回归降维参数估计模型。研究发现,剔除共线性变量之后,对未来物价预期指数有正向影响作用的变量是:未来收入信心指数、大额消费品消费意愿比例、房价预期上涨比例,并且影响强度依次减弱;有负向影响作用的变量是:当期物价满意指数、当期收入感受指数、房价过高难以接受比例,并且影响强度依次减弱。
The future price expectation index refers to the diffusion index of residents'price judgment for the next quarter.This paper uses the data of 37 quarters of urban residents from the first quarter of 2009 to the first quarter of 2018 to construct a ridge regression and Lasso regression dimension reduction parameter estimation model with the future price expectation index as the explanatory variable,and the current income perception index as the explanatory variable.The study finds that after removing the collinearity variables,the variables that have a positive impact on the future price expectation index are:the future income confidence index,the proportion of the willingness to consume large consumer goods,the proportion of the expected rise in housing prices,and the impact intensity is weakened in turn;the variables that have a negative impact are:the current price satisfaction index,the current income feeling index,and the proportion of the housing prices being too high to accept,and the intensity of influence is decreased in turn.
作者
周燕芳
温有栋
杨君
Zhou Yanfang;Wen Youdong;Yang Jun(School of Statistics,Jiangxi University of Finance and Economics,Nanchang 330013,China;School of Economics and Management,East China Jiaotong University,Nanchang 330013,China)
出处
《统计与决策》
CSSCI
北大核心
2020年第4期40-44,共5页
Statistics & Decision
基金
国家自然科学基金资助项目(71861012)
江西省教育厅科学技术研究项目(GJJ160513)。
关键词
未来物价预期指数
岭回归
Lasso回归
收入信心指数
future price expectation index
ridge regression
lasso regression
income confidence index
