empiricalCdf function

List<CdfPoint> empiricalCdf(List<num> values)

Builds the empirical CDF of values: one CdfPoint per DISTINCT value in ascending order, with p the running fraction of samples ≤ that value. Returns an empty list for no samples. Does not mutate values.

Example:

empiricalCdf(<num>[1, 2, 2, 3]);
// [CdfPoint(1, 0.25), CdfPoint(2, 0.75), CdfPoint(3, 1.0)]

Audited: 2026-06-12 11:26 EDT

Implementation

List<CdfPoint> empiricalCdf(List<num> values) {
  if (values.isEmpty) return <CdfPoint>[];
  final List<num> sorted = List<num>.of(values)..sort();
  final int n = sorted.length;
  final List<CdfPoint> points = <CdfPoint>[];
  int i = 0;
  while (i < n) {
    final num value = sorted[i];
    // Advance past every duplicate of this value so each distinct value yields a
    // single point whose p reflects all samples ≤ it.
    int j = i;
    while (j < n && sorted[j] == value) {
      j++;
    }
    points.add(CdfPoint(value, j / n));
    i = j;
  }
  return points;
}