add_base.mcgf_rs {mcgf}R Documentation

Add base model outputted from fit_base() to an mcgf_rs object.

Description

Add base model outputted from fit_base() to an mcgf_rs object.

Usage

## S3 method for class 'mcgf_rs'
add_base(x, fit_base_ls, fit_s_ls, fit_t_ls, sep = FALSE, old = FALSE, ...)

Arguments

x

An mcgf_rs' object.

fit_base_ls

Output from the fit_base() function.

fit_s_ls

Pure spatial model outputted from the fit_base() function. Used only when sep = TRUE.

fit_t_ls

Pure temporal model outputted from the fit_base() function. Used only when sep = TRUE.

sep

Logical; TRUE if spatial and temporal models are fitted separately.

old

Logical; TRUE if the old base model needs to be kept. The lag and horizon of the new model are assumed to be the same as that of the old model.

...

Additional arguments. Not in use.

Details

After fitting the base model by fit_base(), the results can be added to x by add_base(). To supply the base model directly, use base<- to add the base model; the value must contain the same output as add_base.mcgf() or add_base.mcgf_rs().

Value

x with newly added attributes of the base model.

See Also

Other functions on fitting an mcgf_rs: add_lagr.mcgf_rs(), fit_base.mcgf_rs(), fit_lagr.mcgf_rs(), krige.mcgf_rs(), krige_new.mcgf_rs()

Examples

data(sim2)
sim2_mcgf <- mcgf_rs(sim2$data, dists = sim2$dists, label = sim2$label)
sim2_mcgf <- add_acfs(sim2_mcgf, lag_max = 5)
sim2_mcgf <- add_ccfs(sim2_mcgf, lag_max = 5)

# Fit a regime-switching pure spatial model
fit_spatial <-
    fit_base(
        sim2_mcgf,
        lag_ls = 5,
        model_ls = "spatial",
        par_init_ls = list(c(c = 0.00005, gamma = 0.5)),
        par_fixed_ls = list(c(nugget = 0))
    )

# Fit a regime-switching pure temporal model
fit_temporal <-
    fit_base(
        sim2_mcgf,
        lag_ls = 5,
        model_ls = "temporal",
        par_init_ls = list(
            list(a = 0.8, alpha = 0.8),
            list(a = 0.1, alpha = 0.1)
        )
    )

# Store the fitted models to 'sim2_mcgf'
sim2_mcgf <- add_base(sim2_mcgf,
    fit_s_ls = fit_spatial,
    fit_t_ls = fit_temporal,
    sep = TRUE
)

# Fit a regime-switching separable model
fit_sep <- fit_base(
    sim2_mcgf,
    lag_ls = 5,
    model_ls = "sep",
    par_init_ls = list(list(
        c = 0.00005,
        gamma = 0.5,
        a = 0.5,
        alpha = 0.5
    )),
    par_fixed_ls = list(c(nugget = 0))
)

# Store the newly fitted model, and keep the old fit
sim2_mcgf <- add_base(sim2_mcgf, fit_base_ls = fit_sep, old = TRUE)
model(sim2_mcgf, model = "base", old = TRUE)

[Package mcgf version 1.1.1 Index]