论文部分内容阅读
本文在给出了不完全数据全信息回归估计算法的基础上,用 Monte-Carlo 法验证了估计的偏性与方差。结果表明全信息回归系数估计值是渐近无偏的;方差较小,说明它充分利用了数据提供的信息。
In this paper, based on the incomplete data full information regression estimation algorithm, the Monte-Carlo method is used to verify the bias and variance of the estimation. The results show that the estimated value of the regression coefficient of the whole information is asymptotically unbiased; the variance is small, indicating that it makes full use of the information provided by the data.