A PSI Training Course: Missing Data

Presented by Michael O'Kelly

Venue: Crowne Plaza, Heathrow

Date: 6^th-7^th March 2018

For further details or to register: http://www.psiweb.org and click on events

The aim of this course is to provide participants with an understanding of missing data, its link with what is to be estimated in a study (the “estimand”), and statistical modelling approaches. The 2 day course includes workshops: participants will undertake a number of practical exercises on missing data in SAS.

The course will provide participants the opportunity to gain insight into some of the more useful new methodologies for missing data, with a view to being at the service of the real scientific question of interest. Multiple imputation (MI) will be emphasised – due to this method’s flexibility.

Attendees will require a laptop with access to SAS.

The following topics will be covered:

·         History of research into missing data

·         Prevention of missing data and impact on study power

·         Missing data and its relation to the estimand

·         Estimands and their models

·         Multiple imputation I: models for missing data

·         Weighting I: weighting for missing data

·         Multiple imputation II: methods for non-continuous endpoints

·         Weighting II: augmenting weighted data with model estimates

·         Composite endpoints

·         Case studies