Wilson Confidence Interval

The statistical method AVO uses to compute confidence bounds on rate-based measurements (Wilson, 1927). More accurate than the simpler normal approximation, particularly for small samples or extreme proportions. Every rate that feeds VS is a binomial proportion; the Wilson interval is propagated through each pillar formula and through the final VS combination to produce an interval on the headline score itself. The propagation is intentionally conservative — rate intervals are treated as if independent, slightly overstating true interval width. Reported intervals are graded high, medium, low, or insufficient based on width; insufficient-grade intervals require deferring decisions until probe coverage improves.