Models for Longitudinal and Incomplete Data, Short Course

  • N/A
    Application Deadline
  • 6 days
    Duration
  • Tuition
    400
    Tuition (Year)
    400
    Tuition (Year)
  • English (take IELTS)
    Language
University rank #40 ,
We first present linear mixed models for continuous hierarchical data. The focus lies on the modelers 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.

About

Apart from classical model building strategies, many of which have been implemented in standard statistical software, a number of flexible extensions and additional tools for model diagnosis will be indicated.

Second, 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.
Third, it is oftentimes necessary to consider fully non-linear models for longitudinal data. We will discuss such situations, and place some emphasis on the non-linear mixed-effects model.

Fourth, non-linear mixed models will be discussed. Applications in the PK/PD world will be brought to the front. Fifth, when analyzing hierarchical and longitudinal data, one is often confronted with missing observations, 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.

Methods to properly analyze incomplete data, under flexible assumptions, are presented. Key concepts of sensitivity analysis are introduced.

All developments will be illustrated with worked examples using the SAS System. However, the course is conceived such that it will be of benefit to both SAS users and users of other platforms.

One day of this 6-day training is dedicated to hands-on computation. This includes, not only classroom exercises, but also the option to analyse participants owndata! For the latter aspects, the SAS System will be used.

Detailed Programme Facts

  • Full-time duration 6 days
  • Study intensity Full-time
  • Languages
    • English
  • Delivery mode
    On Campus

Programme Structure

Course Materials
  • A .pdf file with the course material will be made available.
  • Background reading:
    Verbeke, G. and Molenberghs, G. (2000) Linear Mixed Models for Longitudinal Data. New York: Springer.
    Molenberghs, G. and Kenward, M.G. (2007) Missing Data in Clinical Studies. Chichester: John Wiley & Sons.
    Molenberghs, G. and Verbeke, G. (2005) Models for Repeated Discrete Data. New York: Springer.

Audience

The targeted audience includes methodological and applied statisticians and researchers in industry, public health organizations, contract research organizations, and academia.Important: The course will also serve for the Master in Statistics.

Lecturers

  • Geert Verbeke
  • Geert Molenberghs

Geert Molenberghs and Geert Verbeke are editors and authors of several books on the use of linear mixed models for the analysis of longitudinal data (Springer Lecture Notes 1997, Springer Series in Statistics 2000, Springer Series in Statistics 2005, Chapman Hall/CRC 2007)

English Language Requirements

This programme requires students to demonstrate proficiency in English.

Take IELTS test

Academic Requirements

Throughout the course, it will be assumed that the participants are familiar with basic statistical modeling concepts, including linear models (regression and analysis of variance), as well as generalized linear models (logistic and Poisson regression) and basic knowledge of mixed and multilevel models. Moreover, pre-requisite knowledge should also include general estimation and testing theory (maximum likelihood, likelihood ratio). When registering for this course, you have to mention the topics you have followed before and/or indicate where you became acquainted with the requested material.

Tuition Fee Per Year

  • EUR 400 International
  • EUR 400 EU/EEA
  • Staff and students Association KU Leuven and PhD students, non-KU Leuven 400
  • Non profit/social sector 625
  • Private sector 1500

Funding

StudyPortals Tip: Students can search online for independent or external scholarships that can help fund their studies. Check the scholarships to see whether you are eligible to apply. Many scholarships are either merit-based or needs-based.