← Research lab

Epidemiology 2 × 2

Explore cohort, case–control and diagnostic tables.

Rows: exposed / unexposed. Columns: outcome present / absent.

Use counts of independent observations. Matched data, clustered data, weights and adjusted effects require a different analysis.

Your result

Enter your assumptions and run the workshop.

RR = [a/(a+b)]/[c/(c+d)]; OR = ad/bc. Risk differences are absolute percentage-point differences. Case–control sampling cannot directly estimate population risks. Diagnostic mode uses a=true positive, b=false positive, c=false negative, d=true negative. Zero denominators are reported as undefined; no correction is silently added. CDC reference ↗ · FDA diagnostic definitions ↗