Power and Sample Size Calculations for Primary Open Angle Glaucoma / Ocular Hypertension Clinical Trials Accounting for Correlation of Measures among the Time Points across Visits

ARVO Annual Meeting, May 2012

Historically, the correlation among time points within a subject/eye and the requirement of a majority of time points having an upper 95% Confidence Interval less than 1 mmHg has not been overtly accounted for when determining power and sample size for clinical trials in primary open angle glaucoma/ocular hypertension. We propose a method to account for both of these points.

This poster details:

• The importance of accounting for the correlation of measures among time points
• How the number of time points and correlation among time points affect power and sample size
• How these variables affect Type I Error

Authored by:

• Dale Usner, PhD
• Richard Abelson, PhD