bamlss: coef.bamlss – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

coef.bamlss

Extract BAMLSS Coefficients

Description

Methods to extract coefficients of fitted bamlss objects, either coefficients returned from optimizer functions, or samples from a sampler functions.

Method confint.bamlss() produces credible intervals or parameter samples using quantiles.

Usage

## S3 method for class 'bamlss'
coef(object, model = NULL, term = NULL,
  FUN = NULL, parameters = NULL,
  pterms = TRUE, sterms = TRUE,
  hyper.parameters = TRUE, list = FALSE,
  full.names = TRUE, rescale = FALSE, ...)

## S3 method for class 'bamlss'
confint(object, parm, level = 0.95,
  model = NULL, pterms = TRUE, sterms = FALSE,
  full.names = FALSE, hyper.parameters = FALSE, ...)

Arguments

`object`	An object of class `"bamlss"`
`model`	Character or integer. For which model should coefficients be extracted?
`term`	Character or integer. For which term should coefficients be extracted?
`FUN`	A function that is applied on the parameter samples.
`parameters`	If is set to `TRUE`, additionally adds estimated parameters returned from an optimizer function (if available).
`pterms`	Should coefficients of parametric terms be included?
`sterms`	Should coefficients of smooths terms be included?
`hyper.parameters`	For smooth terms, should hyper parameters such as smoothing variances be included?
`list`	Should the returned object have a list structure for each distribution parameter?
`full.names`	Should full names be assigned, indicating whether a term is parametric "p" or smooth "s".
`rescale`	Should parameters of the linear parts be rescaled if the `scale.d` argument in `bamlss.frame` is set to `TRUE`.
`parm`	Character or integer. For which term should coefficients intervals be extracted?
`level`	The credible level which defines the lower and upper quantiles that should be computed from the samples.
`...`	Arguments to be passed to `FUN` and function `samples`.

Value

Depending on argument list and the number of distributional parameters, either a list or vector/matrix of model coefficients.

Examples

## Not run: ## Simulate data.
d <- GAMart()

## Model formula.
f <- list(
  num ~ s(x1) + s(x2) + s(x3),
  sigma ~ s(x1) + s(x2) + s(x3)
)

## Estimate model.
b <- bamlss(f, data = d)

## Extract coefficients based on MCMC samples.
coef(b)

## Now only the mean.
coef(b, FUN = mean)

## As list without the full names.
coef(b, FUN = mean, list = TRUE, full.names = FALSE)

## Coefficients only for "mu".
coef(b, model = "mu")

## And "s(x2)".
coef(b, model = "mu", term = "s(x2)")

## With optimizer parameters.
coef(b, model = "mu", term = "s(x2)", parameters = TRUE)

## Only parameteric part.
coef(b, sterms = FALSE, hyper.parameters = FALSE)

## For sigma.
coef(b, model = "sigma", sterms = FALSE,
  hyper.parameters = FALSE)

## 95 perc. credible interval based on samples.
confint(b)

## End(Not run)

bamlss

Bayesian Additive Models for Location, Scale, and Shape (and Beyond)

v1.1-3

GPL-2 | GPL-3

Authors

Nikolaus Umlauf [aut, cre] (<https://orcid.org/0000-0003-2160-9803>), Nadja Klein [aut] (<https://orcid.org/0000-0002-5072-5347>), Achim Zeileis [aut] (<https://orcid.org/0000-0003-0918-3766>), Meike Koehler [ctb], Thorsten Simon [aut] (<https://orcid.org/0000-0002-3778-7738>), Stanislaus Stadlmann [ctb]

Initial release

2021-01-25