Missing Data in Longitudinal Studies
30 June, 1 July 2011
University of Adelaide
Adelaide, Australia
Strategies for Bayesian Modelling, Sensitivity Analysis, and Causal Inference
About the course:
This course provides a survey of primarily Bayesian approaches to handling missing data in longitudinal studies, and illustrates the use of newly-developed methods for model selection, sensitivity analysis, incorporation of prior information, and causal inference. The emphasis is on Bayesian approaches but the models and methods discussed can be implemented in non-Bayesian settings as well. The course will be roughly divided into five parts: Part 1 course will include a brief review of models for longitudinal data and the basics of Bayesian inference; Part 2 will focus on formal classification of dropout and missing data mechanisms, describe classes of models that can be used to adjust for biases caused by dropout, and the logistics of model fitting and model selection and Bayesian proper imputation; Part 3 will deal with specification and fitting of models to handle non-ignorable (informative) dropout, with emphasis on the role of sensitivity analysis and informative prior distributions for encoding key assumptions; Part 4 will focus on causal inference in the context of incomplete longitudinal data; Part 5 will discuss approaches for handling missing time-varying and baseline covariates. Integrated into the course will be six case studies that illustrate many of the concepts introduced during the course. We will build on each case study to illustrate progressively more complex analyses (e.g. progressing from analysis under MAR, to analysis under MNAR, to use of informative priors and sensitivity analyses).
Target Audience
(a) Professional statisticians working in applied environments where missing data is a key issue and where formal, well justified approaches are needed for making informed inferences; e.g. academic centres running large clinical trials, statisticians working in the pharmaceutical industry, statisticians working for regulatory agencies
(b) Researchers and students from statistics and related fields who are interested in the topic as an area of re-search. The necessary background is a working knowledge of linear and generalized linear models and basics of likelihood-based inference. This would include individuals with graduate degrees in statistics, biostatistics, econometrics and related fields, and advanced students in programs offering these degrees.
About the Instructor
Michael Daniels is Professor and Chair in the Department of Statistics at the University of Florida. Mike has published extensively in the statistical literature on methods for (incomplete) longitudinal data with articles appearing in Biometrics, Biometrika, Biostatistics, Journal of the American Statistical Association, and Statistics in Medicine and has had continuous research funding from the U.S. National Institutes of Health (NIH) since 2001. He recently completed a book, coauthored with Joe Hogan, titled "Missing Data in Longitudinal Studies: Strategies for Bayesian modeling and Sensitivity Analysis" published by Chapman & Hall/CRC Press. He has taught a graduate-level course on incomplete longitudinal data at the University of Florida several times and has given several short courses on missing data and dropout at national and international conferences and government agencies.
Program
Thursday, June 30
8:30-9:00 Registration
9:00-9:45 Motivating Examples
9:45-10:15 Regression for longitudinal data
10:15-10:45 Key concepts in Bayesian inference
10:45-11:15 Coffee Break
11:15-12:15 Missing data mechanisms in longitudinal studies
12:15-12:45 Bayesian approaches to model selection and checking for incomplete
longitudinal data
12:45-1:45 Lunch
1:45-3:15 Models and methods for ignorable
Missingness
3:15-3:45 Coffee Break
3:45-4:15 Proper Bayesian multiple imputation
4:15-5:15 Models for handling nonignorable missingness
Friday, July 1
9:00-10:30 Sensitivity analysis and informative
Priors (part 1)
10:30-11:00 Coffee Break
11:00-12:30 Sensitivity analysis and informative
Priors (part 2)
12:30-1:30 Lunch
1:30-3:00 Causal inference and missing data in
longitudinal studies
3:00-3:30 Coffee Break
3:30-5:00 Missing covariates
Cost
There are separate regression costs depending upon whether the delegate is a full-time student, and a member of the Statistical Society of Australia. Registration includes a complete set of course notes, and full catering (lunch, morning and afternoon tea) throughout the workshop.
|
|
Student members
|
Student
non-members
|
SSAI
Members
|
Non-members
|
|
Early Bird
(before 16th June)
|
$AUD320
|
$AUD425
|
$AUD625
|
$AUD850
|
|
Regular
(after 15th June)
|
$AUD370
|
$AUD475
|
$AUD675
|
$AUD900
|
Places are limited, so please book early to avoid disappointment!
Online registration is available here. To download a registration form, please click here.
Non-member students wishing to take advantage of the student rate need to use the hard-copy registration form and fax it together with their student id to SSAI, Fax No. 02 6251 0204.
Members need to be logged in with their username and password to take advantage of the member rates!
Venue
University of Adelaide - exact address tba
Travel Expenses
Occasionally workshops have to be cancelled due to a lack of subscription. Please contact the SSAI Office before making any travel arrangements to confirm that the workshop will go ahead, because the SSAI will not be held responsible for any travel or accommodation expenses incurred due to a workshop cancellation.
Cancellation Policy
Cancellations received prior to 23 June 2011 will be refunded in full. Cancellations need to be accompanied by a valid credit card number and expiry date which will be used to put the refund through. After 23 June 2011 no part of the registration fee will be refunded. However, registrations are transferable within the same organisation. Please advise any changes to eo@statsoc.org.au.
Proudly organised by the SSAI Biostatistics Section and the University of Adelaide
