19 Apr module 18: longitudinal and incomplete data
- module 18: longitudinal and incomplete data
16/09/2019 - 18/09/2019
9:30 am - 5:00 pm
Mon 16/09: 9.30 am - 5.00 pm | S5 pc room 1.1
Tue 17/09: 9.30 am - 5.00 pm | S5 pc room 1.1
Wed 18/09: 9.30 am - 5.00 pm | S5 pc room 1.1 43
We begin by presenting linear mixed models for continuous hierarchical data. The focus lies on the modeler’s perspective and on applications. Emphasis will be on model formulation, parameter estimation, and hypothesis testing, as well as on the distinction between the random-effects (hierarchical) model and the implied marginal model. Then, models for non-Gaussian data will be discussed, with a strong emphasis on generalized estimating equations (GEE) and the generalized linear mixed model (GLMM). To usefully introduce this theme, a brief review of the classical generalized linear modeling framework will be presented. Similarities and differences with the continuous case will be discussed. The differences between marginal models, such as GEE, and random-effects models, such as the GLMM, will be explained in detail. Extending the framework of the linear mixed model and the generalized linear mixed model, we will discuss nonlinear mixed models. When analyzing hierarchical and longitudinal data, one is often confronted with missing data, i.e., scheduled measurements have not been made, due to a variety of (known or unknown) reasons. It will be shown that, if no appropriate measures are taken, missing data can cause seriously jeopardize results, and interpretation difficulties are bound to occur. Precisely, a framework will be sketched to handle incomplete data. Simple and simplistic methods will be commented on. Methods to properly analyze incomplete data, under flexible assumptions, are presented. These include ignorable likelihood analysis, ignorable Bayesian analysis, weighted estimating equations, and multiple imputation. To conclude, the issue of sensitivity to non-verifiable assumption is discussed, and addressed through sensitivity analyses. All developments will be illustrated with worked examples using the SAS System. Hands-on SAS exercises will supplement the lectures.
- Theme 1: Linear mixed models, model formulation, parameter interpretation, hierarchical versus marginal model interpretation, estimation and inference, empirical Bayes
- Theme 2: Model families for discrete outcomes, marginal models, generalized estimating equations (GEE)
- Theme 3: Generalized linear mixed models, estimation methods (Laplace, MQL, PQL, Quadrature), comparison with GEE
- Theme 4: Nonlinear mixed models, rationale, worked examples
- Theme 5: Missing data mechanisms, problems with nonrandom dropout (i.e., bias, loss of efficiency, etc.), modeling frameworks to handle dropout (selection, pattern mixture and shared parameter models), sensitivity analyses
- Session A: Linear mixed models
- Session B: Generalized estimating equations and generalized linear mixed models
- Session C: Missing data
Throughout the course, it is assumed that the participants are familiar with basic statistical modeling, including linear models (regression and analysis of variance), as well as generalized linear models (logistic and Poisson regression). Moreover, pre-requisite knowledge should also include general estimation and testing theory (maximum likelihood, likelihood ratio, etc.). As the annotated programs and output in the lectures as well as the practicals are based on SAS, a working knowledge of this software is required.
Geert Verbeke is Professor in Biostatistics at KU Leuven and Universiteit Hasselt in Belgium. He received the B.S. degree in mathematics (1989) from the Katholieke Universiteit Leuven, the M.S. in biostatistics (1992) from Universiteit Hasselt, and earned a Ph.D. in biostatistics (1995) from the Katholieke Universiteit Leuven. Geert Verbeke has published extensively on longitudinal data analyses. He has held visiting positions at the Gerontology Research Center and the Johns Hopkins University (Baltimore, MD). Geert Verbeke is Past President of the Belgian Region of the International Biometric Society, International Program Chair for the International Biometric Conference in Montreal (2006), Board Member of the American Statistical Association. He is past Joint Editor of the Journal of the Royal Statistical Society, Series A (2005–2008) and Co-editor of Biometrics (2010–2012). He is the director of the Leuven Center for Biostatistics and statistical Bioinformatics (L-BioStat), and vice-director of the Interuniversity Institute for Biostatistics and statistical Bioinformatics (I-BioStat), a joint initiative of the Hasselt and Leuven universities in Belgium. He served on the ASA Board as International Representative. Geert Verbeke is Vice-President and Incompling President (2020–2021) of the International Biometric Society.
Geert Molenberghs is Professor of Biostatistics at the Universiteit Hasselt and Katholieke Universiteit Leuven in Belgium. He received the B.S. degree in mathematics (1988) and a Ph.D. in biostatistics (1993) from the Universiteit Antwerpen. Prof. Molenberghs published methodological work on surrogate markers in clinical trials, categorical data, longitudinal data analysis, and on the analysis of non-response in clinical and epidemiological studies. He served as Joint Editor for Applied Statistics (2001-2004), Co-editor of Biometrics (2007–2009) and as President of the International Biometric Society (2004–2005). He was Co-editor of Biostatistics (2010–2012). He was elected Fellow of the American Statistical Association and received the Guy Medal in Bronze from the Royal Statistical Society. He has held visiting positions at the Harvard School of Public Health (Boston, MA). He is founding director of the Center for Statistics at Hasselt University and currently the director of the Interuniversity Institute for Biostatistics and statistical Bioinformatics, I-BioStat, a joint initiative of the Hasselt and Leuven universities.
Venue: University of Ghent
Venue Phone: +32 9 264 48 84
Venue Website: https://www.flames-statistics.com/summer-school/venue/Address: