Multiple Imputation and Posterior Simulation for Multivariate Missing Data in Longitudinal Studies
BiometricsPublished 1 December 2000Open access
Minzhi Liu, Jeremy M. G. Taylor, Thomas R. Belin
Citations71
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A random coefficients model is developed to accommodate incomplete multivariate continuous longitudinal data and the multiple imputation procedure is compared to the weighting approach of Robins, Rotnitzky, and Zhao that can be used to address similar data structures.
Abstract
This paper outlines a multiple imputation method for handling missing data in designed longitudinal studies. A random coefficients model is developed to accommodate incomplete multivariate continuous longitudinal data. Multivariate repeated measures are jointly modeled; specifically, an i.i.d. normal model is assumed for time-independent variables and a hierarchical random coefficients model is assumed for time-dependent variables in a regression model conditional on the time-independent variables and time, with heterogeneous error variances across variables and time points. Gibbs sampling is used to draw model parameters and for imputations of missing observations. An application to data from a study of startle reactions illustrates the model. A simulation study compares the multiple imputation procedure to the weighting approach of Robins, Rotnitzky, and Zhao (1995, Journal of the American Statistical Association 90, 106-121) that can be used to address similar data structures.
Keywords
Computer ScienceMathematics
Wiley series in probability and statisticsMultiple Imputation for Nonresponse in Surveys
20,606 Citations1987Donald B. Rubin
Statistical ScienceInference from Iterative Simulation Using Multiple Sequences
16,747 Citations1992Andrew Gelman, Donald B. Rubin
The focus is on applied inference for Bayesian posterior distributions in real problems, which often tend toward normal- ity after transformations and marginalization, and the results are derived as normal-theory approximations to exact Bayesian inference, conditional on the observed simulations.
BiometricsRandom-Effects Models for Longitudinal Data
8,915 Citations1982Nan M. Laird, James H. Ware
A unified approach to fitting these models, based on a combination of empirical Bayes and maximum likelihood estimation of model parameters and using the EM algorithm, is discussed.
Analysis of Incomplete Multivariate Data
5,989 Citations1997Joseph L. Schafer
The Normal Model Methods for Categorical Data Loglinear Models Methods for Mixed Data and Inference by Data Augmentation Methods for Normal Data provide insights into the construction of categorical and mixed data models.
TechnometricsAnalysis of Incomplete Multivariate Data
5,644 Citations2000David E. Booth, Joseph L. Schafer
Journal of the American Statistical AssociationMultiple Imputation after 18+ Years
2,949 Citations1996Donald B. Rubin
Journal of the American Statistical AssociationMultiple Imputation After 18+ Years
2,693 Citations1996Donald B. Rubin
A description of the assumed context and objectives of multiple imputation is provided, and a review of the multiple imputations framework and its standard results are reviewed.
Journal of the American Statistical AssociationEstimation of Regression Coefficients When Some Regressors are not Always Observed
2,647 Citations1994James M. Robins, Andrea Rotnitzky +1 more
Journal of the American Statistical AssociationAnalysis of Semiparametric Regression Models for Repeated Outcomes in the Presence of Missing Data
1,542 Citations1995James M. Robins, Andrea Rotnitzky +1 more
BiometricsUnbalanced Repeated-Measures Models with Structured Covariance Matrices
1,346 Citations1986Robert I. Jennrich, Mark Schluchter
This work addresses the question of how to analyze unbalanced or incomplete repeated-measures data through maximum likelihood analysis using a general linear model for expected responses and arbitrary structural models for the within-subject covariances.
Journal of the American Statistical AssociationAdjusting for Nonignorable Drop-Out Using Semiparametric Nonresponse Models
987 Citations1999Daniel O. Scharfstein, Andrea Rotnitzky +1 more
Statistical ScienceMultiple-Imputation Inferences with Uncongenial Sources of Input
753 Citations1994Xiao‐Li Meng
When it is desirable to conduct inferences under models for nonresponse other than the original imputation model, a possible alternative to recreating imputation models is to incorporate appropriate importance weights into the standard combining rules.
BiometricsIntent-to-Treat Analysis for Longitudinal Studies with Drop-Outs
386 Citations1996Roderick J. A. Little, Linda Yau
This work proposes a method that involves multiple imputation of the missing values following drop-out based on an "as treated" model, using actual dose after drop- out if this is known, or imputed doses that incorporate a variety of plausible alternative assumptions if unknown.
Statistics in MedicineTOWARD A CURSE OF DIMENSIONALITY APPROPRIATE (CODA) ASYMPTOTIC THEORY FOR SEMI‐PARAMETRIC MODELS
350 Citations1997James M. Robins, Ya’acov Ritov
It is shown that any statistician who ignores the randomization probabilities is unable to construct nominal 95 per cent confidence intervals for the true treatment effect, and proposes a curse of dimensionality appropriate (CODA) asymptotic theory for inference in non- and semi-parametric models.
Computational Statistics & Data AnalysisPartially parametric techniques for multiple imputation
325 Citations1996Nathaniel Schenker, Jeremy M. G. Taylor
This paper compares partially parametric and fully parametric regression-based multiple-imputation methods for handling data sets with missing values and provides an example of how multiple imputation can be used to combine information from two cohorts to estimate quantities that cannot be estimated directly from either one of the cohorts separately.
Journal of the American Statistical AssociationAlternative Methods for CPS Income Imputation
130 Citations1986Martin David, Roderick J. A. Little +2 more
Journal of the American Statistical AssociationA Weighted Estimating Equation for Missing Covariate Data with Properties Similar to Maximum Likelihood
110 Citations1999Stuart R. Lipsitz, Joseph G. Ibrahim +1 more
BiometricsMultiple Imputation and Posterior Simulation for Multivariate Missing Data in Longitudinal Studies
71 Citations2000Minzhi Liu, Jeremy M. G. Taylor +1 more
A random coefficients model is developed to accommodate incomplete multivariate continuous longitudinal data and the multiple imputation procedure is compared to the weighting approach of Robins, Rotnitzky, and Zhao that can be used to address similar data structures.
BiometricsInference for the Association between Coefficients in a Multivariate Growth Curve Model
32 Citations1995David M. Zucker, Gary O. Zerbe +1 more
This paper deals with longitudinal data involving one or more response variables and irregular follow-up times, with each response variable postulated to follow a linear growth curve model.
PsychophysiologyAutonomic, electroencephalographic, and myogenic activity accompanying startle and its habituation during mid‐childhood
23 Citations1996Edward M. Ornitz, Andrew Russell +2 more
Tonic cardiac activity was facilitated, suggesting sensitization of state, as proposed in the dual-process theory of habituation, and startle habituated, pre- and poststartle myogenic, alpha, and cardiac activities failed to habituate.
Statistics in MedicineEstimating correlation between alternative measures of disease progression in a longitudinal study
19 Citations1990Mark Schluchter
This paper shows how the maximum likelihood estimate of the correlation coefficient and a 100(1 - alpha) per cent confidence interval can be obtained and an example estimating the correlation between GFR and inverse serum creatinine slopes in patients with chronic renal disease is given.