Abstract
This chapter reviews statistical methods for the analysis of longitudinal data that are commonly found in health services research. The chapter begins by discussing issues inherent in longitudinal data and provides historical background on early methods that were used to analyze data of this type. Next, mixed-effects regression models (MRMs) and covariance-pattern models (CPMs) for longitudinal data are introduced with a focus on linear models for normally distributed outcomes. As an illustration of the use of these methods in practice, MRMs and CPMs are applied to data from the Women Entering Care (WECare) study, a longitudinal depression treatment study. Finally, extensions and alternatives to these models are briefly described. Key phrases: mixed-effects models; random-effects models; covariance-pattern models; effect sizes.
Similar content being viewed by others
References
Berkhof J, Snijders TAB. Variance component testing in multilevel models. J Educ Behav Stat. 2001;26:133–52.
Bock RD. Multivariate statistical methods in behavioral research. New York: McGraw-Hill; 1975.
Bock RD. Within-subject experimentation in psychiatric research. In: Gibbons RD, Dysken MW, editors. Statistical and methodological advances in psychiatric research. New York: Spectrum; 1983a. p. 59–90.
Bock RD. The discrete Bayesian. In: Wainer H, Messick S, editors. Modern advances in psychometric research. Hillsdale: Erlbaum; 1983b. p. 103–15.
Bock RD. Measurement of human variation: a two stage model. In: Bock RD, editor. Multilevel analysis of educational data. New York: Academic; 1989.
Bryk AS, Raudenbush SW. Hierarchical linear models: applications and data analysis methods. Newbury Park: Sage; 1992.
Chi EM, Reinsel GC. Models for longitudinal data with random effects and AR(1) errors. J Am Stat Soc. 1989;84:452–9.
Conaway MR. Analysis of repeated categorical measurements with conditional likelihood methods. J Am Stat Assoc. 1989;84:53–61.
Daniels MJ, Hogan JW. Reparameterizing the pattern mixture model for sensitivity analyses under informative dropout. Biometrics. 2000;56:1241–8.
Daniels MJ, Hogan JW. Missing data in longitudinal studies: strategies for Bayesian modeling and sensitivity analysis. New York: Chapman & Hall/CRC; 2008.
de Leeuw J, Kreft I. Random coefficient models for multilevel analysis. J Educ Stat. 1986;11:57–85.
Demirtas H, Schafer JL. On the performance of random-coefficient pattern-mixture models for nonignorable dropout. Stat Med. 2003;22:2553–75.
Dempster AP, Rubin DB, Tsutakawa RK. Estimation in covariance component models. J Am Stat Soc. 1981;76:341–53.
Diggle PJ, Heagerty P, Liang K-Y, Zeger SL. Analysis of longitudinal data. 2nd ed. New York: Oxford University Press; 2002.
Fitzmaurice GM, Laird NM, Ware JH. Applied longitudinal analysis. 2nd ed. Hoboken: Wiley; 2012.
Gibbons RD. Trend in correlated proportions. PhD thesis, University of Chicago, Department of Psychology, 1981.
Gibbons RD, Bock RD. Trend in correlated proportions. Psychometrika. 1987;52:113–24.
Gibbons RD, Hedeker D, Waternaux CM, Davis JM. Random regression models: a comprehensive approach to the analysis of longitudinal psychiatric data. Psychopharmacol Bull. 1988;24:438–43.
Goldstein H. Multilevel mixed linear model analysis using iterative generalized least squares. Biometrika. 1986;73:43–56.
Goldstein H. Nonlinear multilevel models, with an application to discrete response data. Biometrika. 1991;78:45–51.
Goldstein H. Multilevel statistical models. 4th ed. Hoboken: Wiley; 2011.
Grady JJ, Helms RW. Model selection techniques for the covariance matrix for incomplete longitudinal data. Stat Med. 1995;14:1397–416.
Guo W, Ratcliffe SJ, Ten Have TR. A random pattern-mixture model for longitudinal data with dropouts. J Am Stat Assoc. 2004;99:929–37.
Hardin JW, Hilbe JM. Generalized estimating equations. 2nd ed. New York: Chapman and Hall; 2012.
Hedeker D. Random regression models with autocorrelated errors. PhD thesis, University of Chicago, Department of Psychology, 1989.
Hedeker D, Gibbons RD. Longitudinal data analysis. New York: Wiley; 2006.
Hui SL, Berger JO. Empirical Bayes estimation of rates in longitudinal studies. J Am Stat Assoc. 1983;78:753–9.
Ibrahim J, Molenberghs G. Missing data methods in longitudinal studies: a review (with discussion). TEST. 2009;18:1–43.
Kaplan D, George R. Evaluating latent growth models through ex post simulation. J Educ Behav Stat. 1998;23:216–35.
Kenward MG, Molenberghs G. Parametric models for incomplete continuous and categorical longitudinal data. Stat Methods Med Res. 1999;8(1):51–83.
Laird NM. Missing data in longitudinal studies. Stat Med. 1988;7:305–15.
Laird NM, Ware JH. Random-effects models for longitudinal data. Biometrics. 1982;38:963–74.
Liang K-Y, Zeger SL. Longitudinal data analysis using generalized linear models. Biometrika. 1986;73:13–22.
Little RJA. Modeling the drop-out mechanism in repeated-measures studies. J Am Stat Assoc. 1995;90:1112–21.
Little RJA, Rubin DB. Statistical analysis with missing data. 2nd ed. New York: Wiley; 2002.
Longford NT. A fast scoring algorithm for maximum likelihood estimation in unbalanced mixed models with nested random effects. Biometrika. 1987;74:817–27.
Longford NT. Random coefficient models. New York: Oxford University Press; 1993.
Miranda J, Chung JY, Green BL, Krupnick J, Siddique J, Revicki DA, Belin T. Treating depression in predominantly low-income young minority women. J Am Med Assoc. 2003;290:57–65.
Miranda J, Chung JY, Green BL, Krupnick J, Siddique J, Revicki DA. One year outcomes of treating depression in predominantly low-income young minority women. J Clin Consult Psychol. 2006;74:99–111.
Muth’en BO. Latent variable analysis: growth mixture modeling and related techniques for longitudinal data. In: Kaplan D, editor. Handbook of quantitative methodology for the social sciences. Newbury Park: Sage; 2004.
Muth’en B, Shedden K. Finite mixture modeling with mixture outcomes using the em algorithm. Biometrics. 1999;55:463–9.
Muth’en B, Brown CH, Masyn K, Jo B, Khoo ST, Yang CC, Wang CP, Kellam SG, Carlin JB, Liao J. General growth mixture modeling for randomized preventive interventions. Biostatistics. 2002;3(4):459–75.
Muth’en BO, Brown CH, Leuchter A, Hunter A. General approaches to analysis of course: applying growth mixture modeling to randomized trials of depression medication. In: Shrout PE, editor. Causality and psychopathology: finding the determinants of disorders and their cures. Washington, DC: American Psychiatric Publishing; 2009. Forthcoming.
Neuhaus JM, Kalbfleisch JD, Hauck WW. A comparison of cluster-specific and population-averaged approaches for analyzing correlated binary data. Int Stat Rev. 1991;59:25–35.
Potthoff RF, Roy SN. A generalized multivariate analysis of variance model useful especially for growth curve problems. Biometrika. 1964;51:313–6.
Raudenbush SW, Bryk AS. A hierarchical model for studying school effects. Sociol Educ. 1986;59:1–17.
Raudenbush SW, Bryk AS. Hierarchical linear models. 2nd ed. Thousand Oaks: Sage; 2002.
Rubin DB. Inference and missing data. Biometrika. 1976;63:581–92.
Siddique J, Brown CH, Hedeker D, Duan N, Gibbons RD, Miranda J, Lavori PW. Missing data in longitudinal trials–part B, analytic issues. Psychiatr Ann. 2008;38(12):793–801.
Siddique J, Chung JY, Brown CH, Miranda J. Comparative effectiveness of medication versus cognitive behavioral therapy in a randomized controlled trial of low-income young minority women with depression. J Consult Clin Psychol. 2012;80:995–1006.
Singer JD, Willett JB. Applied longitudinal data analysis. New York: Oxford University Press; 2003.
Stiratelli R, Laird NM, Ware JH. Random-effects models for serial observations with binary response. Biometrics. 1984;40:961–71.
Strenio JF, Weisberg HI, Bryk AS. Empirical Bayes estimation of individual growth curve parameters and their relationship to covariates. Biometrics. 1983;39:71–86.
Verbeke G, Molenberghs G. Linear mixed models for longitudinal data. New York: Springer; 2000.
Weiss RE. Modeling longitudinal data. New York: Springer; 2005.
Wolfinger RD. Covariance structure selection in general mixed models. Commun Stat Simul Comput. 1993;22:1079–106.
Wong GY, Mason WM. The hierarchical logistic regression model for multilevel analysis. J Am Stat Assoc. 1985;80:513–24.
Xu W, Hedeker D. A random-effects models for classifying treatment response in longitudinal clinical trials. J Biopharm Stat. 2002;11:253–73.
Zeger SL, Liang KY. Longitudinal data analysis for discrete and continuous outcomes. Biometrics. 1986;42:121–30.
Zeger SL, Liang KY, Albert PS. Models for longitudinal data: a generalized estimating equation approach. Biometrics. 1988;44:1049–60.
Acknowledgments
The authors wish to thank Jeanne Miranda for use of the WECare data. Dr. Siddique’s work was supported by grant K07 CA154862-01 from the National Cancer Institute and R03 HS018815-01 from the Agency for Healthcare Research and Quality. Dr. Hedeker’s work was supported by Award Number P01 CA098262 from the National Cancer Institute. Dr. Gibbons’ work was supported by R01 MH8012201 from the National Institute of Mental Health. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Cancer Institute, Agency for Healthcare Research and Quality, or the National Institutes of Health.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Science+Business Media LLC
About this entry
Cite this entry
Siddique, J., Hedeker, D., Gibbons, R.D. (2017). Analysis of Repeated Measures and Longitudinal Data in Health Services Research. In: Sobolev, B., Gatsonis, C. (eds) Methods in Health Services Research. Health Services Research. Springer, Boston, MA. https://doi.org/10.1007/978-1-4939-6704-9_1-1
Download citation
DOI: https://doi.org/10.1007/978-1-4939-6704-9_1-1
Received:
Accepted:
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4939-6704-9
Online ISBN: 978-1-4939-6704-9
eBook Packages: Springer Reference MedicineReference Module Medicine