Distribution index · Exponential · Mixed-data likelihood
The two-parameter Weibull family models positive magnitudes with a monotone hazard. RMC.Numerics uses constructor order
For
The survival and quantile functions are
For
The mode is zero for
For exact positive observations,
RMC.BestFit substitutes the Weibull density, CDF, and survival in the full mixed-data likelihood, including censoring, intervals, uncertain-observation convolution, and threshold counts. Parameter trends permit nonstationary Weibull.GetParameterConstraints; both parameters must remain positive.
Short records may not distinguish scale from shape well, and zero observations interact with the boundary density: it diverges when
private static (double Density, double Cdf, double Quantile) EvaluateWeibull()
{
var distribution = new global::Numerics.Distributions.Weibull(1500.0, 2.0);
return Evaluate(distribution, value: 2200.0, nonExceedanceProbability: 0.99);
}The scale and evaluated quantile carry the observation units. Shape 2 implies an increasing hazard; “hazard” must be interpreted in terms of the modeled random variable and sampling design, not automatically as chronological flood risk.
Required checks include density normalization, CDF/quantile inversion, theoretical moments, boundary values for shapes below/equal/above one, and the
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] W. Weibull, “A statistical distribution function of wide applicability,” Journal of Applied Mechanics, vol. 18, pp. 293–297, 1951.