Disproportionality Calculator (PRR and ROR)
Enter report counts from a spontaneous reporting database. The tool returns the proportional reporting ratio (PRR), the reporting odds ratio (ROR), their 95% confidence intervals and chi-squared.
Formulas
| Measure | Formula |
|---|---|
| PRR | [a / (a + b)] ÷ [c / (c + d)]; 95% CI = exp(ln PRR ± 1.96 √(1/a − 1/(a+b) + 1/c − 1/(c+d))) |
| ROR | (a / b) ÷ (c / d) = ad / bc; 95% CI = exp(ln ROR ± 1.96 √(1/a + 1/b + 1/c + 1/d)) |
| Chi-squared | Pearson 2×2 chi-squared, shown with and without Yates' continuity correction |
| Signal criteria (Evans 2001) | 3 or more cases, PRR at least 2, chi-squared at least 4. This tool applies them to the Yates-corrected value, the more conservative choice. |
Disproportionality shows that an event is reported more often than expected for a drug. It does not measure incidence or prove causation. Reporting can be distorted by publicity, stimulated reporting and duplicate reports, so every signal needs clinical evaluation (book, Chapter 16).