Trial Design
Primary Endpoint
A primary endpoint is the pre-specified outcome measure on which a clinical trial's conclusions about efficacy or safety are principally based, used to power the sample size calculation and to test the trial's main hypothesis.
The primary endpoint must be clinically meaningful, measurable, and sensitive to the treatment's mechanism. Examples include overall survival in oncology, HbA1c change in diabetes, ACR20 response in rheumatoid arthritis, and FEV1 change in COPD.
Trials may pre-specify co-primary endpoints (both must succeed) or hierarchical multiple primary endpoints (tested in fixed sequence to control family-wise error). The choice has major statistical-power implications and must be locked in the SAP before unblinding.
Related terms
Endpoint (Clinical Trial)
A clinical trial endpoint is a defined, measurable outcome that determines whether the intervention being studied has the intended effect; it is the variable on which the trial's success or failure is statistically evaluated.
Secondary Endpoint
A secondary endpoint is a pre-specified outcome measure that supports interpretation of the primary endpoint or evaluates additional treatment effects, but is not the principal basis for the trial's conclusion.
Statistical Analysis Plan (SAP)
A Statistical Analysis Plan (SAP) is a detailed technical document that specifies, before database lock, every statistical analysis to be performed on a clinical trial's data, including primary and secondary endpoint analyses, handling of missing data, multiplicity adjustments, and sensitivity analyses.
Sample Size Calculation
Sample size calculation is the statistical process of determining the number of participants required for a clinical trial to detect a specified treatment effect with a defined Type 1 error rate, statistical power, and assumptions about variability.
See how Kitsa applies this in your trials
Kitsa's agentic AI compresses protocol development, site selection, and patient pre-screening from months into weeks.
Request a demo