On summary measures analysis of the linear mixed effects model for repeated measures when data are not missing completely at random. 1999

R J Little, and T Raghunathan
Department of Biostatistics and Institute for Social Research, University of Michigan, 1420 Washington Heights, Ann Arbor, MI 48109-2029, USA. rlittle@umich.edu

Subjects often drop out of longitudinal studies prematurely, yielding unbalanced data with unequal numbers of measures for each subject. A simple and convenient approach to analysis is to develop summary measures for each individual and then regress the summary measures on between-subject covariates. We examine properties of this approach in the context of the linear mixed effects model when the data are not missing completely at random, in the sense that drop-out depends on the values of the repeated measures after conditioning on fixed covariates. The approach is compared with likelihood-based approaches that model the vector of repeated measures for each individual. Methods are compared by simulation for the case where repeated measures over time are linear and can be summarized by a slope and intercept for each individual. Our simulations suggest that summary measures analysis based on the slopes alone is comparable to full maximum likelihood when the data are missing completely at random but is markedly inferior when the data are not missing completely at random. Analysis discarding the incomplete cases is even worse, with large biases and very poor confidence coverage.

UI MeSH Term Description Entries
D008137 Longitudinal Studies Studies in which variables relating to an individual or group of individuals are assessed over a period of time. Bogalusa Heart Study,California Teachers Study,Framingham Heart Study,Jackson Heart Study,Longitudinal Survey,Tuskegee Syphilis Study,Bogalusa Heart Studies,California Teachers Studies,Framingham Heart Studies,Heart Studies, Bogalusa,Heart Studies, Framingham,Heart Studies, Jackson,Heart Study, Bogalusa,Heart Study, Framingham,Heart Study, Jackson,Jackson Heart Studies,Longitudinal Study,Longitudinal Surveys,Studies, Bogalusa Heart,Studies, California Teachers,Studies, Jackson Heart,Studies, Longitudinal,Study, Bogalusa Heart,Study, California Teachers,Study, Longitudinal,Survey, Longitudinal,Surveys, Longitudinal,Syphilis Studies, Tuskegee,Syphilis Study, Tuskegee,Teachers Studies, California,Teachers Study, California,Tuskegee Syphilis Studies
D008954 Models, Biological Theoretical representations that simulate the behavior or activity of biological processes or diseases. For disease models in living animals, DISEASE MODELS, ANIMAL is available. Biological models include the use of mathematical equations, computers, and other electronic equipment. Biological Model,Biological Models,Model, Biological,Models, Biologic,Biologic Model,Biologic Models,Model, Biologic
D010352 Patient Dropouts Discontinuance of care received by patient(s) due to reasons other than full recovery from the disease. Dropout, Patient,Dropouts, Patient,Patient Dropout
D003198 Computer Simulation Computer-based representation of physical systems and phenomena such as chemical processes. Computational Modeling,Computational Modelling,Computer Models,In silico Modeling,In silico Models,In silico Simulation,Models, Computer,Computerized Models,Computer Model,Computer Simulations,Computerized Model,In silico Model,Model, Computer,Model, Computerized,Model, In silico,Modeling, Computational,Modeling, In silico,Modelling, Computational,Simulation, Computer,Simulation, In silico,Simulations, Computer
D003627 Data Interpretation, Statistical Application of statistical procedures to analyze specific observed or assumed facts from a particular study. Data Analysis, Statistical,Data Interpretations, Statistical,Interpretation, Statistical Data,Statistical Data Analysis,Statistical Data Interpretation,Analyses, Statistical Data,Analysis, Statistical Data,Data Analyses, Statistical,Interpretations, Statistical Data,Statistical Data Analyses,Statistical Data Interpretations
D006801 Humans Members of the species Homo sapiens. Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D016013 Likelihood Functions Functions constructed from a statistical model and a set of observed data which give the probability of that data for various values of the unknown model parameters. Those parameter values that maximize the probability are the maximum likelihood estimates of the parameters. Likelihood Ratio Test,Maximum Likelihood Estimates,Estimate, Maximum Likelihood,Estimates, Maximum Likelihood,Function, Likelihood,Functions, Likelihood,Likelihood Function,Maximum Likelihood Estimate,Test, Likelihood Ratio
D016014 Linear Models Statistical models in which the value of a parameter for a given value of a factor is assumed to be equal to a + bx, where a and b are constants. The models predict a linear regression. Linear Regression,Log-Linear Models,Models, Linear,Linear Model,Linear Regressions,Log Linear Models,Log-Linear Model,Model, Linear,Model, Log-Linear,Models, Log-Linear,Regression, Linear,Regressions, Linear

Related Publications

R J Little, and T Raghunathan
March 2011, Epidemiology (Cambridge, Mass.),
R J Little, and T Raghunathan
July 2022, American journal of orthodontics and dentofacial orthopedics : official publication of the American Association of Orthodontists, its constituent societies, and the American Board of Orthodontics,
R J Little, and T Raghunathan
December 2013, Structural equation modeling : a multidisciplinary journal,
R J Little, and T Raghunathan
November 2021, Pharmaceutical statistics,
R J Little, and T Raghunathan
November 2020, European journal of ophthalmology,
R J Little, and T Raghunathan
March 2011, Journal of biopharmaceutical statistics,
R J Little, and T Raghunathan
January 2011, Neural networks : the official journal of the International Neural Network Society,
R J Little, and T Raghunathan
August 2006, Statistics in medicine,
R J Little, and T Raghunathan
September 2011, Biometrical journal. Biometrische Zeitschrift,
Copied contents to your clipboard!