R: Estimate transfer function models by Simple Refined...

armax.sriv.fit {hydromad}

R Documentation

Estimate transfer function models by Simple Refined Instrumental Variables method.

Description

Calibrate unit hydrograph transfer function models (armax or expuh) using Simple Refined Instrumental Variables (SRIV) method.

Usage

armax.sriv.fit(DATA,
           order = hydromad.getOption("order"),
           delay = hydromad.getOption("delay"),
           noise.order = hydromad.getOption("riv.noise.order"),
           fixed.ar = NULL,
           ...,
           fallback = TRUE,
           na.action = na.pass,
           epsilon = hydromad.getOption("sriv.epsilon"),
           max.iterations = hydromad.getOption("sriv.iterations"))

expuh.sriv.fit(DATA,
              order = hydromad.getOption("order"),
              delay = hydromad.getOption("delay"),
              quiet = FALSE,
              ...)

Arguments

`DATA`	a `ts`-like object with named columns: `U` observed input time series. `Q` observed output time series.
`order`	the transfer function order. See `armax`.
`delay`	delay (lag time / dead time) in number of time steps. If missing, this will be estimated from the cross correlation function.
`noise.order`
`fixed.ar`
`...`	further arguments may include prefilter initX trace ~~Describe `trace` here~~
`fallback`
`na.action`
`epsilon`
`max.iterations`
`quiet`	to suppress the message when re-fitting if non-physical poles (i.e. negative or imaginary poles) are detected.

Details

In normal usage, one would not call these functions directly, but rather specify the routing fitting method for a hydromad model using that function's rfit argument. E.g. to specify fitting an expuh routing model by SRIV one could write

hydromad(..., routing = "expuh", rfit = "sriv")

which uses the default order, hydromad.getOption("order"), or

hydromad(..., routing = "expuh", rfit = list("sriv", order = c(2,1))).

Value

a tf object, which is a list with components

`coefficients`	the fitted parameter values.
`fitted.values`	the fitted values.
`residuals`	the residuals.
`delay`	the (possibly fitted) delay time.

Author(s)

Felix Andrews felix@nfrac.org

References

Young, P. C. (2008). The refined instrumental variable method. Journal Européen des Systèmes Automatisés 42 (2-3), 149-179. http://dx.doi.org/10.3166/jesa.42.149-179

Jakeman, A. J., G. A. Thomas and C. R. Dietrich (1991). System Identification and Validation for Output Prediction of a Dynamic Hydrologic Process, Journal of Forecasting 10, pp. 319–346.

Ljung, Lennart (1999). System Identification: Theory for the User (second edition). Prentice Hall. pp. 224-226, 466.

Examples

U <- ts(c(0, 0, 0, 1, rep(0, 30), 1, rep(0, 20)))
Y <- expuh.sim(lag(U, -1), tau_s = 10, tau_q = 2, v_s = 0.5, v_3 = 0.1)
set.seed(0)
Yh <- Y * rnorm(Y, mean = 1, sd = 0.2)
fit1 <- armax.sriv.fit(ts.union(U = U, Q = Yh),
                       order = c(2, 2), warmup = 0)
fit1
xyplot(ts.union(observed = Yh, fitted = fitted(fit1)),
       superpose = TRUE)

[Package hydromad version 0.9-18 Index]