The performance of the full information maximum likelihood estimator in multiple regression models with missing data
The performance of the full information maximum likelihood estimator in multiple regression models with missing data
复制标题
DOI：
10.1177/00131640121971482
复制
发表时间：
2001-10-01
影响因子：
2.7
通讯作者：
Enders, CK
中科院分区：
文献类型：
--
作者：
Enders, CK
蒙特卡罗模拟检验了最近可用的全信息最大似然(FIML)估计器在具有缺失数据的多元回归模型中的性能。研究了四个自变量(缺失数据技术、缺失率、样本量和相关性大小)对回归系数偏差、R-2偏差和回归系数抽样变异性的影响。根据鲁宾的缺失数据理论，研究了三种缺失数据模式：完全随机缺失、随机缺失和非随机缺失。图案。结果表明，在所研究的条件下，FIML估计优于三种特殊方法(逐列删除、成对删除和均值补偿)，FM参数估计总体上比三种特殊方法具有更小的偏差和更小的抽样变异性。
A Monte Carlo simulation examined the performance of a recently available full information maximum likelihood (FIML) estimator in a multiple regression model with missing data. The effects of four independent variables were examined (missing data technique, missing data rate, sample size, and correlation magnitude) on three outcome measures regression coefficient bias, R-2 bias, and regression coefficient sampling variability. Three missing data patterns were examined based on Rubin's missing data theory: missing completely at random, missing at random, and a nonrandom. pattern. Results indicated that FIML estimation was superior to the three ad hoc techniques (listwise deletion, pairwise deletion, and mean imputatiom) across the conditions studied, FM parameter estimates generally had less bias and less sampling variability than the three ad hoc methods.