Technical reference | Rating curve
| Model | Mathematical treatment | Principal API |
|---|---|---|
| AR( |
Autoregressive models |
AutoRegressive, ARAnalysis
|
| MA( |
Moving-average models |
MovingAverage, MAAnalysis
|
| ARIMA( |
Integrated ARMA |
ARIMA, ARIMAAnalysis
|
| ARIMAX( |
Regression, covariates, trend, and seasonality |
ARIMAX, ARIMAXAnalysis
|
All four models use Gaussian conditional likelihoods on an optional transformed response, bounded marginal parameter priors, Bayesian MCMC as the primary analysis estimator, and posterior-predictive simulation for uncertainty curves. They do not share one interchangeable parameter ordering; use each chapter's crosswalk.
For raw response
where
For ARIMA and ARIMAX with raw training length
Default training window. With conditioning order UseDefaultTrainingSteps is on, the window is
so it trains on 80% of the
When the optional Jeffreys rule is enabled, each model adds the scale contribution
JeffreysScalePrior, separately from each parameter's configured marginal
ParameterPrior; the sum of all pointwise prior components equals the scalar prior likelihood at
valid parameter sets. This classification is diagnostic metadata and does not alter the prior.
The innovation scale domain is finite
Transform.None, logarithmic Box–Cox, fitted Box–Cox, and fitted Yeo–Johnson are supported.
Transformation fitting is preprocessing, not part of [0, TrainingTimeSteps) and then frozen while the transform is applied
to the full response. Consequently, changing holdout values cannot change the training transform,
Jacobian, likelihood, or defaults. The effective read-only TransformLambda is fitted
automatically unless assigned through SetTransformParameters. A manual lambda remains fixed
when only the training window changes; a fitted lambda refits when the response, training window,
or transform type changes. None and logarithmic transforms use canonical lambda zero.
Transform state is rebuilt atomically before numerical results are reused. Existing XML remains
valid; optional invariant-culture TransformLambda and TransformLambdaIsManual attributes
preserve the effective exponent and its provenance through save/open and clone/copy workflows.
The setter's second argument, lambda2, remains accepted but is intentionally ignored for API
compatibility; it is not a shift or offset parameter.
Prediction and simulation share the inverse statistical order but have different conditioning
contracts. ARIMA/ARIMAX first construct intercept, trend, seasonality, exact-date level-covariate,
AR, MA, and innovation contributions on the transformed/highest-difference model scale. For
prediction with
ARAnalysis, MAAnalysis, ARIMAAnalysis, and ARIMAXAnalysis follow the common AnalysisBase lifecycle:
- Validate model data, orders, parameter bounds, training length, and forecast horizon.
- Initialize
BayesianAnalysis, ordinarily with MLE-derived screening/starting behavior managed by the analysis. - Run Bayesian sampling asynchronously with progress and cancellation propagation.
- Select the posterior mean or sampled MAP state for the displayed deterministic curve.
- Generate uncertainty realizations from joint posterior draws and seeded innovations.
- Publish model-scale results, original-scale curves, DIC, RMSE, and analysis metadata.
ForecastingTimeSteps on an analysis means steps beyond the complete observed response in the published result. Internally the analysis passes observedCount - TrainingTimeSteps + ForecastingTimeSteps to Predict, so the returned curve includes the training region, held-out observed region, and future horizon. Forecasting is capped at 100 steps.
The uncertainty result is posterior predictive: parameter uncertainty, innovation noise, nonlinear inverse transformation, and—where applicable—covariate extension are combined. It is not a confidence band for the conditional mean. Report the seed, posterior draw count, transform, training endpoint, and covariate scenario.
For an integrated transformed model, a stable and nearly symmetric forecast distribution on the
transformed scale can become strongly asymmetric after the inverse transform. Innovation variance
also accumulates with forecast horizon when Transform.None are not directly comparable with intervals from a fitted nonlinear
transform because they represent different fitted models.
Choose orders using scientific plausibility, ACF/PACF as exploratory tools, residual diagnostics, and genuinely held-out predictive performance. ACF/PACF patterns are asymptotic heuristics and are distorted by trend, seasonality, transformations, outliers, and short records. After fitting, examine:
- response and residual time plots;
- residual ACF/PACF and portmanteau checks at hydrologically relevant lags;
- innovation normality and variance stability;
- characteristic roots and their posterior uncertainty;
- chain mixing, R-hat, and ESS under the limitations in MCMC diagnostics;
- holdout coverage and proper scores on the original decision scale;
- sensitivity to training window, transform, order, and covariate specification.
AR, MA, ARIMA, and ARIMAX analyses compute AIC/BIC from each model's data log likelihood evaluated at the stored MAP; prior-density terms are excluded. The values agree with MLE criteria only when every active prior is constant and MAP coincides with the constrained MLE. The default Jeffreys scale option is nonconstant, so analyses using it—or any informative prior—should use DIC, WAIC, or verified PSIS-LOO for Bayesian comparison rather than treating the MAP-evaluated fields as conventional AIC/BIC.
The verification suite checks this routing independently for AR, MA, ARIMA, ARIMAX, and rating curve, with an analytical flat-prior order-zero Gaussian comparison.
| Configuration | Estimation likelihood | Forecast/predictive simulation |
|---|---|---|
| AR/MA, no fitted transform | Available subject to conditional-likelihood assumptions | Available subject to diagnostic checks |
| AR/MA with fitted transform | Available with training-only frozen lambda | Back-transform is median-like; transform uncertainty omitted |
| ARIMA/ARIMAX with |
Available | Available, subject to ARIMAX covariate scenario |
| ARIMA with |
Conditional likelihood can be inspected | Prediction conditions on observed training states; simulation uses explicit observed/zero initialization anchors |
| ARIMAX with |
Available with exact-date level covariates and conditional Jacobian alignment | Prediction conditions on observed training states with exact-date covariates; simulation uses explicit observed/zero initialization anchors |
| ARIMA transformed/differenced simulation | — | Available; full model-scale recursion, integration, then one inverse transform |
| ARIMAX transformed/differenced simulation | — | Available; all components on model scale, exact-date level covariates, integration, then one inverse transform |
These capabilities remain conditional on the likelihood, transformation, initialization, and covariate assumptions described above. Ordinary pointwise LOO for a conditional time-series likelihood is not leave-future-out validation: neighboring observations can retain information about an omitted time. Assess forecasting with a chronological holdout or rolling-origin experiment.
State the variable and units, interval, calendar/water-year convention, missing-data treatment, training and holdout dates, transformation and fitting subset, model orders, intercept meaning, seasonal period, covariate units/lags/future scenario, priors, sampler/seed, diagnostic thresholds, residual results, parameter roots, forecast target (median/mean/realization), and uncertainty components. Distinguish operational forecasts conditional on known covariates from scenarios requiring future precipitation, regulation, or climate assumptions.
Implementation is under Models/TimeSeries/; orchestration is under Analyses/TimeSeries/. Fast
tests are under RMC.BestFit.Tests/TimeSeriesModels/ and TimeSeriesAnalysis/. Focused numerical
Verification methods are under the matching RMC.BestFit.Verification directories and are run
only by exact fully qualified name; the complete Verification project is not run.
[1] G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed., Wiley, 2015.
[2] R. H. Shumway and D. S. Stoffer, Time Series Analysis and Its Applications, 4th ed., Springer, 2017.
[3] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed., OTexts, 2021.