Random covariances and mixed-effects models for imputing multivariate multilevel continuous data
Author:
- 16 August 2011
- journal article
- research article
- Published by SAGE Publications in Statistical Modelling
- Vol. 11 (4) , 351-370
Abstract
Principled techniques for incomplete data problems are increasingly part of mainstream statistical practice. Among many proposed techniques so far, inference by multiple imputation (MI) has emerged as one of the most popular. While many strategies leading to inference by MI are available in cross-sectional settings, the same richness does not exist in multilevel applications. The limited methods available for multilevel applications rely on the multivariate adaptations of mixed-effects models. This approach preserves the mean structure across clusters and incorporates distinct variance components into the imputation process. In this paper, I add to these methods by considering a random covariance structure and develop computational algorithms. The attraction of this new imputation modelling strategy is to correctly reflect the mean and variance structure of the joint distribution of the data and allow the covariances differ across the clusters. Using Markov chain Monte Carlo techniques, a predictive distribution of missing data given observed data is simulated leading to creation of MIs. To circumvent the large sample size requirement to support independent covariance estimates for the level-1 error term, I consider distributional impositions mimicking random-effects distributions assigned a priori. These techniques are illustrated in an example exploring relationships between victimization and individual and contextual level factors that raise the risk of violent crime.Keywords
This publication has 21 references indexed in Scilit:
- Multilevel models with multivariate mixed response typesStatistical Modelling, 2009
- Using Calibration to Improve Rounding in ImputationThe American Statistician, 2008
- Multiple imputation inference for multivariate multilevel continuous data with ignorable non-responsePhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2008
- An imputation strategy for incomplete longitudinal ordinal dataStatistics in Medicine, 2008
- Plausibility of multivariate normality assumption when multiply imputing non-Gaussian continuous outcomes: a simulation assessmentJournal of Statistical Computation and Simulation, 2008
- A Potential for Bias When Rounding in Multiple ImputationThe American Statistician, 2003
- Markov Chains for Exploring Posterior DistributionsThe Annals of Statistics, 1994
- MACRO‐MICRO INTEGRATION IN THE STUDY OF VICTIMIZATION: A HIERARCHICAL LOGISTIC MODEL ANALYSIS ACROSS SEATTLE NEIGHBORHOODS*Criminology, 1994
- Contextual Effects in Models of Criminal VictimizationSocial Forces, 1993
- Formalizing Subjective Notions about the Effect of Nonrespondents in Sample SurveysJournal of the American Statistical Association, 1977