Distribution index · Log-Pearson Type III · Normal limit
Pearson Type III (PIII) is a shifted, possibly reflected Gamma distribution parameterized in RMC.Numerics by its arithmetic mean
when
Let
For
The quantile follows by the corresponding inverse incomplete-gamma function. At
For positive skew and exact observations, omitting only notation already defined,
The reflected expression applies for negative skew. RMC.BestFit uses the family CDF and density in the complete mixed-data likelihood, including measurement-error convolution and threshold information. Parameter trends predict
Starts and bounds are derived from sample product moments by the Numerics constraint routine and used for default uniform priors. As
private static (double Density, double Cdf, double Quantile) EvaluatePearsonTypeIII()
{
var distribution = new global::Numerics.Distributions.PearsonTypeIII(
1500.0, 400.0, 0.50);
return Evaluate(distribution, value: 2200.0, nonExceedanceProbability: 0.99);
}All but skew use observation units. Positive 0.50 skew creates a finite lower endpoint and unbounded upper tail.
Required evidence includes moment recovery, density normalization for both skew signs, CDF/quantile inversion, reflected-tail support, and continuity to Normal at zero skew. The compiled example guards the public parameter order. The shifted support can include negative values depending on the moments; physical plausibility and rare-tail leverage must be checked.
The distribution verification matrix identifies the current independent formula and fitted-objective comparisons, retained Bayesian/MLE recovery designs, and their distinct acceptance rules. The compiled example guards API compatibility; it does not run an estimator or establish scientific accuracy by itself.
[1] K. Pearson, “Contributions to the mathematical theory of evolution. II. Skew variation in homogeneous material,” Philosophical Transactions of the Royal Society A, vol. 186, pp. 343–414, 1895.