Multiple imputation of missing covariates with non-linear effects and interactions: an evaluation of statistical methods
Open Access
- 10 April 2012
- journal article
- Published by Springer Nature in BMC Medical Research Methodology
- Vol. 12 (1) , 46
Abstract
Multiple imputation is often used for missing data. When a model contains as covariates more than one function of a variable, it is not obvious how best to impute missing values in these covariates. Consider a regression with outcome Y and covariates X and X 2. In 'passive imputation' a value X* is imputed for X and then X 2 is imputed as (X*)2. A recent proposal is to treat X 2 as 'just another variable' (JAV) and impute X and X 2 under multivariate normality.Keywords
This publication has 19 references indexed in Scilit:
- Multiple imputation using chained equations: Issues and guidance for practiceStatistics in Medicine, 2010
- 8. How to Impute Interactions, Squares, and other Transformed VariablesSociological Methodology, 2009
- Is plasma vitamin C an appropriate biomarker of vitamin C intake? A systematic review and meta-analysisNutrition Journal, 2007
- 4. Regression with Missing Ys: An Improved Strategy for Analyzing Multiply Imputed DataSociological Methodology, 2007
- Multiple imputation of discrete and continuous data by fully conditional specificationStatistical Methods in Medical Research, 2007
- Proper and Improper Multiple ImputationInternational Statistical Review, 2003
- Comparing nonnested Cox modelsBiometrika, 2002
- Inference for imputation estimatorsBiometrika, 2000
- Asymptotic Results for Multiple ImputationThe Annals of Statistics, 1988
- A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for HeteroskedasticityEconometrica, 1980