Multiple Imputation for Missing Data
Open Access
- 1 February 2000
- journal article
- Published by SAGE Publications in Sociological Methods & Research
- Vol. 28 (3), 301-309
- https://doi.org/10.1177/0049124100028003003
Abstract
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 are 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.Keywords
This publication has 7 references indexed in Scilit:
- An Empirical Evaluation of the Predictive Mean Matching Method for Imputing Missing ValuesSociological Methods & Research, 1997
- Multiple Imputation after 18+ YearsJournal of the American Statistical Association, 1996
- A multiple imputation strategy for clinical trials with truncation of patient dataStatistics in Medicine, 1995
- The Analysis of Social Science Data with Missing ValuesSociological Methods & Research, 1989
- Multiple Imputation for Interval Estimation from Simple Random Samples with Ignorable NonresponseJournal of the American Statistical Association, 1986
- The central role of the propensity score in observational studies for causal effectsBiometrika, 1983
- Formalizing Subjective Notions about the Effect of Nonrespondents in Sample SurveysJournal of the American Statistical Association, 1977