cadence.predict: Predict conditional distribution parameters from a fitted...

In CaDENCE: Conditional Density Estimation Network Construction and Evaluation

Description

Predict conditional distribution parameters from a fitted CDEN model. The returned value is a matrix with columns corresponding to the parameters of the probability distribution specified in the distribution argument passed to cadence.fit.

Usage

cadence.predict(x, fit)

Arguments

x	matrix with number of rows equal to the number of samples and number of columns equal to the number of predictor variables.
fit	list returned by cadence.fit.

Value

a matrix with number of rows equal to that of x and columns corresponding to the parameters of the distribution argument passed to cadence.fit.

See Also

cadence.fit, optim, rprop

Examples

    data(FraserSediment)
    lnorm.distribution.fixed <- list(density.fcn = dlnorm,
                                     parameters = c("meanlog", "sdlog"),
                                     parameters.fixed = "sdlog",
                                     output.fcns = c(identity, exp))
    fit <- cadence.fit(x = FraserSediment$x.1970.1976,
                       y = FraserSediment$y.1970.1976,
                       hidden.fcn = identity, maxit.Nelder = 100,
                       trace.Nelder = 1, trace = 1,
                       distribution = lnorm.distribution.fixed)
    pred <- cadence.predict(x = FraserSediment$x.1977.1979, fit = fit)
    matplot(pred, type = "l")

CaDENCE documentation built on May 2, 2019, 6:05 a.m.