cmod {gRim}

Graphical Gaussian model

Description

Specification of graphical Gaussian model. The 'c' in the name cmod refers to that it is a (graphical) model for 'c'ontinuous variables

Usage

cmod(
  formula,
  data,
  marginal = NULL,
  fit = TRUE,
  maximal_only = FALSE,
  details = 0
)

Arguments

formula

Model specification in one of the following forms: 1) a right-hand sided formula, 2) as a list of generators. Notice that there are certain model specification shortcuts, see Section 'details' below.

data

Data in one of the following forms: 1) A dataframe or 2) a list with elements cov and n.obs (such as returned by the cov.wt() function.)

marginal

Should only a subset of the variables be used in connection with the model specification shortcuts.

fit

Should the model be fitted.

maximal_only

Should only maximal generators be retained.

details

Control the amount of output; for debugging purposes.

Details

The independence model can be specified as ~.^1 and the saturated model as ~.^.. The marginal argument can be used for specifying the independence or saturated models for only a subset of the variables.

Value

An object of class cModel (a list)

Author(s)

Søren Højsgaard, [e-mail]

See Also

dmod, mmod, ggmfit

Examples

## Graphical Gaussian model
data(carcass)
cm1 <- cmod(~ .^., data=carcass)

## Stepwise selection based on BIC
cm2 <- backward(cm1, k=log(nrow(carcass)))

## Stepwise selection with fixed edges
cm3 <- backward(cm1, k=log(nrow(carcass)),
 fixin=matrix(c("LeanMeat", "Meat11", "Meat12", "Meat13",
                "LeanMeat", "Fat11", "Fat12", "Fat13"),
                 ncol=2))