摘要
文章提出了含内生性时间不变效应变量的残差自回归误差分量模型,并推导了模型参数的两阶段最小二乘估计方法。为验证参数估计方法的正确性,应用蒙特卡洛模拟法,将模型与固定效应模型和随机效应模型进行了对比。通过均方根误差这一指标发现,本文提出的参数估计方法可以较好地对该类面板数据模型的参数作出精确估计。
This paper puts forward a one-way error components model containing endogeneity and time-invariant effects and deduces the two-stage least square（LS） parameter estimation method. In order to test the correctness of the parameter estimation method, the paper employs Monte Carlo simulation method to compare the model with fixed effect model and random effect model. The result of Root Mean Square Error shows that the proposed method is able to give an accurate parameter estimation of the panel data model.
作者
伊晟
任献花
Yi Sheng;Ren Xianhua(School of Economics and Management, Shanghai University of Sport, Shanghai 200438, Chin;Basic Teaching Department, Shanghai Information Technology School, Shanghai 200331, China)
出处
《统计与决策》
CSSCI
北大核心
2018年第8期35-37,共3页
Statistics & Decision
基金
中国博士后科研基金资助项目(2016M600327)
