LONGITUDINAL
DATA ANALYSIS
SPRING 2017
|
Instructor: |
Guan-Hua Huang, Ph.D. |
|
|
Office: 423 Joint Education Hall |
|
|
Phone: 03-513-1334 |
|
|
Email: ghuang@stat.nctu.edu.tw |
|
Class meetings: |
Monday 13:20-16:20 at 406
Joint Education
Hall |
|
Office hours: |
By
appointment |
|
Class website: |
|
|
Credit: |
Three (3) credits |
COURSE
SUMMARY
Longitudinal data consist of multiple measures over
time on an individual. This type of data occurs extensively in both
observational and experimental biomedical studies, as well as in studies in
sociology and applied economics. This course will provide an introduction to
the principals and methods for the analysis of longitudinal data. While some theoretical statistical detail is given (at the level of
appropriate for a Master’s student in Statistics), the primary focus will be on
data analysis and interpretation.
The objects of his course are
Ÿ To identify features of longitudinal data and explain the roles of
longitudinal data in studying real data phenomenon.
Ÿ To use a generalized linear model to make inferences about the
relationship between responses and explanatory variables while accounting for
the correlation among repeated responses for an individual.
Ÿ To use marginal, random effects, or transition models for longitudinal
data when the repeated observations are binary, count, or Gaussian/non-Gaussian
continuous.
Ÿ To familiarize the usage of statistical software implementing these longitudinal
data analytic methodologies.
Ÿ To provide references for your future research.
HANDOUTS
AND TEXTBOOKS
Handouts corresponding to each lecture
will be available on the class website before each class. Reading assignments are from the following book:
Ÿ
Diggle PJ, Heagerty P, Liang KY and Zeger SL (2002). Analysis
of Longitudinal Data, 2nd edition. Oxford University Press.
PREREQUISITES
Students
are expected to have background on undergraduate probability, and mathematical
statistics. Some knowledge on (generalized) linear regression will be helpful.
METHOD
OF STUDENT EVALUATION
The course grade will be based on 4 homework assignments (50%), 1 midterm exam (20%), and 1 final exam (30%).
COURSE OUTLINE
Diggle PJ, Heagerty P, Liang KY and Zeger SL (2002). Analysis of Longitudinal Data, 2nd
edition. (ALD).
|
Module |
Topic |
|
|
1 |
Introduction
and examples of longitudinal data Ÿ
Introduction and examples Ÿ
Notation for longitudinal data Ÿ
Models for longitudinal data |
ALD Chapter 1 |
|
2 |
Exploring
longitudinal data Ÿ
Exploring longitudinal data Ÿ
Exploring correlation structure of longitudinal data |
ALD Chapter 3 |
|
3 |
Linear
modes for longitudinal data Ÿ
Introduction, overview and simple example Ÿ
Correlation models Ÿ
Inferences Ÿ
Evaluating covariance models Ÿ
Sensitivity to covariance/correlation model and robust variance Ÿ
Exploiting the empirical variance estimator- generalized estimating
equations (GEE) Ÿ
Where have we been? |
ALD Chapter 4 |
|
4 |
Linear
mixed models for longitudinal data Ÿ
Introduction Ÿ
Linear mixed models for longitudinal data: example Ÿ
Details of model building: inference Ÿ
Model evaluation for linear mixed models Ÿ
Parameterization of random effects Ÿ
Estimating individual trajectories |
ALD Chapter 4 |
|
5 |
GLM for
longitudinal data Ÿ
Marginal models Ÿ
Random effects models Ÿ
Transition models |
ADL Chapters 7, 8, 9, and 10 |