Confidence Intervals: Additional Commentary

Abstract

Focus in this chapter falls on two-sided confidence intervals. A two-sided confidence interval constitutes a range of values that are defined by the lower limit and the upper limit of the interval placed around the treatment effect calculated from the trial, which is now referred to as the treatment effect point estimate. The confidence interval is a range of values that is likely to cover the true but unknown population treatment effect with a specified degree of certainty. Three commonly used levels are the 90, 95, and 99% confidence levels. This chapter explains that, when considering the information provided by confidence intervals in their review process, regulatory agencies focus on the limit that represents the ‘worst case scenario.’ For efficacy considerations, the lower limit represents the least likely benefit. For safety considerations, the upper limit represents the greatest risk.