三维面板结构VAR模型的估计  

Estimation of SVAR Model for 3D Panel Structure

作　　者：叶小青[1] 王维峰[1] Ye Xiaoqing;Wang Weifeng(School of Mathematics and Statistics,South-Central Minzu University,Wuhan 430074,China)

机构地区：[1]中南民族大学数学与统计学学院,武汉430074

出　　处：《统计与决策》2022年第2期33-36,共4页Statistics & Decision

基　　金：国家自然科学基金青年项目(11901584);湖北省自然科学基金资助项目(BZY21007)。

摘　　要：文章构建了三维面板结构VAR模型,并提出参数估计的一致性方法,编制估计程序,仿真模拟有限样本性质。结果表明:在给定N_(1)、N_(2)的情况下,随着T的增加,参数的估计值与真值的偏差逐渐减少,并逼近于0;当T固定时,逐渐增大N_(1)、N_(2),偏误逐渐减小,也都趋近于0。随着样本容量的增大,参数估计量的标准误均有逐渐减小的趋势。通过JB检验发现参数估计量都接受服从正态分布的原假设,具有较好的正态性。This paper constructs the SVAR model for 3 D panel structure,proposes the consistency method of parameter estimation,and thencompiles the estimation program and simulates the properties of finite samples.The results are shown as follows:Given N_(1) and N_(2),with the increase of T,the deviation between the estimated value and the real value of parameters decreases gradually and approaches 0;when T is fixed,N_(1) and N_(2) are gradually increased,the bias decreases gradually and approaches0;with the increase of sample size,the standard errors of parameter estimators tend to decrease gradually.The JB test shows that the parameter estimators all accept the null hypothesis of normal distribution and have good normality.

关 键 词：三维面板数据模型 结构VAR 一致性 正态性 

分 类 号：F064.1[经济管理—政治经济学]