Evaluation and Selection of Statistical Analyses for Diary Data in Dry Eye Studies

Patient symptom diaries are a commonly used method to collect efficacy data in clinical trials, such as those for dry eye treatments. Typically, patients are asked to report symptom severity several times per day over the course of a study that may last weeks or even months. To avoid multiplicity from daily comparisons, summary variables, e.g. average score or area under the curve (AUC), can be derived from the repeated measurements of the diary data for evaluating treatment effects. A mixed model approach can also be used to evaluate overall treatment differences accounting for the correlation within each subject. There are different correlation structures that can be utilized. One or more of these methods are usually proposed to analyze data from these diary entries, but to date, systematic comparisons of different analytical methods are lacking. In order to compare these different methods, simulations were performed to evaluate each methodology in terms of power and risk of type I error inflation.

This poster details:

• Various statistical methodologies commonly used to analyze diary data
• Evaluation of each methodology in terms of power and risk of Type I Error inflation
• Recommended mixed model approach based on simulated analysis

Authored by:

• Hui-Chun T. Hsu, ScM
• Kathryn Kennedy, PhD
• Dale Usner, PhD
• Dale Kennedy, PhD
• Richard Abelson, PhD