<- Previous: Bivariate Analysis | Back to Index | Next: Rating Curve ->
CoincidentFrequencyAnalysis propagates a fitted bivariate probability model through a deterministic tabulated response
The upstream BivariateAnalysis supplies two continuous marginal distributions and a fitted copula. The user supplies:
- strictly ascending primary ordinates
$x_0,\ldots,x_{M-1}$ ; - strictly ascending secondary ordinates
$y_0,\ldots,y_{N-1}$ ; - an
$M\times N$ response matrix$r_{ij}=g(x_i,y_j)$ ; and - the number
$K$ of output response bins.
BestFit requires
| Symbol | Meaning |
|---|---|
| random forcing variables with fixed or posterior-varying marginals | |
| deterministic response of interest | |
| marginal CDFs | |
| fitted bivariate copula CDF | |
| supplied response at |
|
| real-space boundary of the |
|
| boundary in copula space | |
| Normal probability-paper coordinate for the primary grid | |
|
|
|
| CDF of the derived response | |
| response annual exceedance probability when the inputs represent annual events |
The units of
For a monotone response, the exact derived CDF is
where $x^(z,y)$ solves $g(x^,y)=z$. BestFit approximates (1) by partitioning the
The implementation scans the complete response matrix for
and creates SetZOutputValues supports deserialization and restoration; a new CreateFrequencyAnalysisResultsAsync call rebuilds this grid from (2).
The real-space edges are
They are mapped to
Thus all lower-tail
For posterior realization
after clamping the probability to
again clamped to the same open interval.
Interpolation in Normal-score space is exactly what the implementation does. It coincides with linear interpolation in
For output
The boundary identities
Equation (7) is a column-bin quadrature. Accuracy depends on response smoothness, grid density, tail coverage, and the suitability of assigning the entire
The copula posterior from the upstream BivariateAnalysis is the required draw source.
MarginalXChain and MarginalYChain are optional. Let
An absent marginal chain is excluded from BayesianAnalysis.PRNGSeed generates one without-replacement index row for every source:
Rows are generated in fixed semantic order: copula, X marginal when present, then Y marginal
when present. Realization
with absent marginal parameter blocks replaced by their point estimates. This is independent
product-posterior propagation across separately fitted stages, not a joint MCMC fit. Longer
chains contribute from their complete retained range rather than only their first
For every BayesianAnalysis.PointEstimator. CFA's BayesianAnalysis does not
run a chain; its nonnegative PRNGSeed controls result-generation pairing. A fixed seed,
semantic source order, and retained order reproduce the exact finite mapping. Source or chain
reordering targets the same product distribution but need not reproduce identical finite output.
If the copula chain has no output draws, the deterministic point-estimate path remains available:
the mean curve is copied from the point curve and confidence limits are NaN. The generated
mapping is cached transiently so GetEmpiricalDistribution(index) returns the exact realization
used by the aggregate result. The cache is regenerated deterministically after loading and is
invalidated with derived results when a supplied chain or the resampling seed changes. Index
arrays are not serialized. Saved CFA uncertainty summaries created by earlier versions must be
reprocessed to use the corrected coupling policy.
The response matrix is held fixed for every realization. Hydraulic parameter, routing-model, terrain, operating-rule, and numerical-model uncertainty are therefore absent unless the user represents them outside this API.
The response below is a monotone maximum-pool-elevation table indexed by peak flow and flood volume. The upstream bivariate analysis must be successfully estimated before RunAsync.
private static CoincidentFrequencyAnalysis ConfigureCoincidentFrequency(
BivariateAnalysis fittedJointModel)
{
double[] peakFlow = { 1_000, 2_000, 3_000, 4_000 };
double[] floodVolume = { 10, 20, 30 };
double[,] maximumPoolElevation =
{
{ 1_205.1, 1_206.3, 1_207.4 },
{ 1_208.0, 1_209.5, 1_211.0 },
{ 1_211.2, 1_213.0, 1_214.8 },
{ 1_214.0, 1_216.1, 1_218.3 }
};
return new CoincidentFrequencyAnalysis(
fittedJointModel,
peakFlow,
floodVolume,
maximumPoolElevation)
{
NumberOfBins = 100
};
}After configuration, call Validate(), examine every error and warning, and only then call RunAsync(). Report the flow, volume, and elevation units with the result. A useful sensitivity analysis varies grid resolution, response-domain extent, copula family, both marginals, and optional marginal posterior chains.
- Monotonicity is mandatory. Small response noise that reverses a column or row causes validation failure. Smooth only with a physically defensible method that preserves the governing model.
-
The tails are collapsed in
$Y$ . All$Y<e_1$ mass uses column 0 and all$Y>e_{N-1}$ mass uses column$N-1$ . Extend the response grid when these regions matter. -
The primary axis is extrapolated. Sparse end segments can dominate rare-response probabilities. Plot
$(r_{ij},\zeta_i)$ by column and inspect the extrapolated slopes. -
The output domain is finite. The generated
$z_k$ values cover only the supplied response minimum and maximum, even though column inversion extrapolates internally. -
AEP semantics are inherited. Calling (8) an annual exceedance probability requires the fitted
$(X,Y)$ pairs to represent annual trials. Event-based or peaks-over-threshold inputs require an exposure/rate conversion outside this analysis. - No response error model is present. The surface is deterministic and exactly known to the algorithm.
- Grid refinement is not an uncertainty interval. Compare successively refined surfaces and treat numerical convergence separately from statistical posterior uncertainty.
- Probability clipping is numerical protection. It prevents infinite Normal scores; it also imposes a finite effective tail boundary.
Implementation: Analyses/Bivariate/CoincidentFrequencyAnalysis.cs, with posterior index
generation in Analyses/Support/PosteriorIndexResampler.cs, upstream probability operations in
Models/BivariateDistribution/BivariateDistribution.cs, and pinned Numerics copulas. Fast tests
cover source-row separation, optional-chain fallback, cache invalidation, aggregate/accessor
identity, seed persistence, and the pre-existing numerical and lifecycle contracts. The focused
CoincidentFrequencyPosteriorResampling_MatchesIndependentClosedFormOracle method passes a
Normal-sum product-posterior oracle at maximum absolute mean tolerance 0.02 and credible-limit
tolerance 0.05; its raw-paired negative control misses by at least 0.10.
No external verification claim is made for a project-specific response surface. For review, archive the surface-generation model, input version, units, grid-convergence study, and deterministic reproduction command alongside the BestFit project.
[1] A. Sklar, “Fonctions de répartition à n dimensions et leurs marges,” Publ. Inst. Statist. Univ. Paris, vol. 8, pp. 229–231, 1959.
[2] R. B. Nelsen, An Introduction to Copulas, 2nd ed. New York, NY, USA: Springer, 2006.
[3] S.-C. Kao and R. S. Govindaraju, “Probabilistic structure of storm surface runoff considering the dependence between average intensity and storm duration of rainfall events,” Water Resour. Res., vol. 43, W06410, 2007, doi: 10.1029/2006WR005564.
[4] A.-C. Favre, S. Quessy, and M. H. T. T. Nguyen, “Multivariate hydrological frequency analysis using copulas,” Water Resour. Res., vol. 40, W01101, 2004, doi: 10.1029/2003WR002456.
<- Previous: Bivariate Analysis | Back to Index | Next: Rating Curve ->