Multiple imputation for missing data - A cautionary tale

被引：452

作者：

Allison, PD ^{[1
]}

机构：

[1] Univ Penn, Philadelphia, PA 19104 USA

来源：

SOCIOLOGICAL METHODS & RESEARCH | 2000年 / 28卷 / 03期

关键词：

D O I：

10.1177/0049124100028003003

中图分类号：

O1 [数学]; C [社会科学总论];

学科分类号：

03 ; 0303 ; 0701 ; 070101 ;

摘要：

Two algorithms for producing multiple imputations for missing data are evaluated with simulated data. Software using a propensity score classifier with the approximate Bayesian bootstrap produces badly biased estimates of regression coefficients when data on predictor variables ape missing at random or missing completely at random. On the other hand a regression-based method employing the data augmentation algorithm produces estimates with little or no bias.

引用

页码：301 / 309

页数：9

共 12 条

[1]

GLYNN R, 1985, THESIS HARVARD U SCH

[2]

KING G, 1999, UNPUB ANAL INCOMPLET

[3] An empirical evaluation of the predictive mean matching method for imputing missing values [J].