|
Abstract:
|
Clinical trial endpoints are traditionally either physical or laboratory responses. However, such endpoints fail to reflect how patients feel or function in their daily activities. Quality of life issues often contribute to patient attrition in clinical trials. Many researchers often resort to ad hoc methods (e.g. case-deletion or mean imputation) when they are faced with missing data, which can lead to biased results. An alternative to these ad hoc methods is multiple imputation. Pattern mixture models, involving restriction methods and multiple imputation, are often used to handle data under the Not Missing at Random (NMAR) assumption. The purpose of this presentation is to introduce pattern mixture models, restriction methods, and to introduce a new pattern-mixture model. The new method will be illustrated using quality-of-life data.
|
