Mixed effect frameworks in the analysis of longitudinal data
DOI:
https://doi.org/10.15305/ijrci/v2i1/82Keywords:
Longitudinal data, Clustering, Mixed effect model, Fixed effects, Random effects, Maximum likelihood estimation.Abstract
Longitudinal research generates data with correlated measurements and clustered data structures. The main interest in longitudinal studies is to find the change in outcome over time and to analyze the influence of predictor variables on the outcome. Model-based approach is a powerful tool to integrate the multiple measurements and complexity of such data. Mixed effect models provide the framework to identify the role of individual differences in responses, while incorporating information from multifactorial measures at the individual and group levels to advance our understanding of the underlying components influencing response. This methodology is flexible, could be extended to different data patterns and computes more accurate and stable estimates. Using a multilevel modeling approach, the hierarchical structure can be explicitly modeled. With the availability of standard statistical software for both classical and Bayesian approaches, its applicability has increased in various fields such as genome-wide association studies, understanding of disease/recovery process, disease-marker association and behavioral studies to understand personality traits and health outcomes. This review seeks to focus on the methodological approaches to model multiple failure time data, conceptual issues, arising due to correlation, heterogeneity, and clustering and estimation procedures. The article also emphasizes on their application in data analysis especially in immunology and rheumatology studies.
References
Mills M. The fundamentals of survival and event history analysis, In: Introducing Survival Analysis and Event History Analysis. London: SAGE Publications; 2011. p. 1-17.
Wei LJ, Glidden DV. An overview of statistical methods for multiple failure time data in clinical trials. Statist Med. 1997;16(8):833–9.
Hamerle A. Multiple-spell Regression Models for Duration Data. Appl Statist. 1989;38(1):127-138.
Lim HJ, Zhang X. Additive and multiplicative hazards modeling for recurrent event data analysis. BMC Medical Research Methodology. 2011 Jun 27;11(1):101.
Goldstein H, Browne W, Rasbash J. Multilevel modelling of medical data. Statist. Med. 2002;21:3291-3315.
Guo G, Zhao H. Multilevel modeling for binary data. Annu. Rev. Sociol. 2002;26:441-462.
Glidden D, Vittinghoff E. Modelling clustered survival data from multicentre clinical trials. Statist. Med. 2004;23(3):369-88.
Zhou X, Perkins AJ, Hui SL. Comparisons of software packages for generalized linear multilevel models. The American Statistician 1999;53:282-290.
Li B, Lingsma HF, Steyerberg EW, Lesaffre E. Logistic random effects regression models: a comparison of statistical packages for binary and ordinal outcomes. BMC medical research methodology. 2011;11:77.
Cole SR, Hudgens MG. Survival analysis in infectious disease research: describing events in time. AIDS.2010;24(16):2423-31.
Hubbard A. Chapter 5 Longitudinal Data Models [Internet]. Berkeley: Environment health sciences, school of public health, University of California Online resources. c2006 [updated 2006 March 8].Available from: http://ehs.sph.berkeley.edu/hubbard/longdata/
Meira-Machado L, de Una-Alvarez J, Cadarso-Suarez C, Andersen PK. Multi-state models for the analysis of time-to-event data. Stat Methods Med Res. 2009;18(2):195–222.
Molenberghs G, Lesaffre E. Marginal modelling of Multivariate categorical data. Statist. Med. 1999;18:2237-2255.
Rodelo A. An Overview of Mixed Effects Models [Internet]. California: San Francisco State University Online resources. c2005 [Updated on 2008 Jun 3]. Available from: http://userwww.sfsu.edu/efc/classes/biol710/mixedeffects/Mixed-Effects-Models.pdf
Kwok OM, Underhill AT, Berry JW, Luo W, Elliott TR, Yoon M. Analyzing Longitudinal Data with Multilevel Models: An Example with Individuals Living with Lower Extremity Intra-articular Fractures. Rehabil Psychol. 2008;53(3):370-386.
Hox J. Multilevel Analysis Techniques and Applications. 2nd ed. New York: Routledge publisher; 2010.
Snijders, Tom AB. ‘Fixed and Random Effects’. In: B.S. Everitt and D.C. Howell (eds.), Encyclopedia of Statistics in Behavioral Science. Volume 2, 664-665. Chicester (etc.): Wiley; 2005.
Gibbons RD, Hedeker D. Applications of mixed-effects models in biostatistics. Sankhya: the Indian journal of statistics. 2000;62:70-103.
Altman RM. Lecture 20: Quasi-Likelihood Estimation [Internet]. Simon Fraser University online resources. c2012. Available from: http://people.stat.sfu.ca/~raltman/stat851/851L20.pdf
Stiratelli R, Laird N, Ware JH. Random-Effects Models for Serial Observations with Binary Response. Biometrics. 1984;40(4):961-971.
Carriere I, Bouyer J. Random-effects models for ordinal responses: Application to self-reported disability among older persons. Rev EpidemiolSantePublique. 2006;54:61-72.
McCulloch CE, Neuhaus JM. Misspecifying the Shape of a Random Effects Distribution: Why Getting It Wrong May Not Matter. Statistical Science, 2011;26(3):388-402.
Sepúlveda N, Campino SG, Assefa SA, Sutherland CJ, Pain A, Clark TG. A Poisson hierarchical modelling approach to detecting copy number variation in sequence coverage data. BMC Genomics.2013;14:128.
Chen GK, Witte JS. Enriching the Analysis of Genomewide Association Studies with Hierarchical Modeling. Am. J. Hum. Genet.2007;81:397-404.
Scharpf RB, Ruczinski I, Carvalho B, Doan B, Chakravarti A, Irizarry RA. A multilevel model to address batch effects in copy number estimation using SNP arrays. Biostatistics (Oxford, England). 2011;12:33-50.
Goldin LR, Landgren O. Autoimmunity and Lymphomagenesis. Int J Cancer. 2009;124(7):1497-1502.
Zautra AJ, Fasman R, Parish BP, Davis MC. Daily fatigue in women with osteoarthritis, rheumatoid arthritis, and fibromyalgia. Pain. 2007;128:128-135.
Finan PH, Zautra AJ, Davis MC, Lemery–Chalfant K, Covault J, Tennen H. Genetic Influences on the Dynamics of Pain and Affect in Fibromyalgia. Health Psychology. 2010;29(2)134-142.
Maas T, Nieuwhof C, Passos VL, Robertson C, BoonenA, Landewé RB, et al. Transgenerational occurrence of allergic disease and autoimmunity: general practice-based epidemiological research. Prim Care Respir J. 2014;23.
Barcellini W, Zaja F, Zaninoni A, Imperiali FG, Battista ML, Bona ED, et al. Low dose rituximab in adult patients with idiopathic autoimmune hemolytic anemia: clinical efficacy and biological studies. Blood. 2012;119(16)3691-3697.
Delezuch W, Marttinen P, Kokki H, Heikkinen M, Vanamo K, Pulkki K, et al. Serum and CSF soluble CD26 and CD30 concentrations in healthy pediatric surgical outpatients. Tissue Antigens. 2012;80:368–375.
Gelman A. Multilevel (Hierarchical) Modeling: What It Can and Cannot Do. Technometrics. 2006;48(3):432-435.
Additional Files
Published
Issue
Section
License
Copyright for articles published in this journal is retained by the authors, with first publication rights granted to the ‘Internet Journal of Rheumatology and Clinical Immunology’. All the published content, except where otherwise noted, is licensed under Creative Commons license (CC-BY).
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after the publication of the manuscript in IJRCI, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
