Graph selection for ggm_compare_explore Objects

Source: R/select.ggm_compare_bf.R

Provides the selected graph (of differences) based on the Bayes factor (Williams et al. 2020) .

# S3 method for ggm_compare_explore
select(object, BF_cut = 3, ...)

Arguments

object

An object of class ggm_compare_explore.
BF_cut

Numeric. Threshold for including an edge (defaults to 3).
...

Currently ignored.

Value

The returned object of class select.ggm_compare_explore contains a lot of information that is used for printing and plotting the results. For users of BGGM, the following are the useful objects:

  • adj_10 Adjacency matrix for which there was evidence for a difference.

  • adj_10 Adjacency matrix for which there was evidence for a null relation

  • pcor_mat_10 Selected partial correlation matrix (weighted adjacency; only for two groups).

See also

explore and ggm_compare_explore for several examples.

Examples

# \donttest{

##################
### example 1: ###
##################
# data
Y <- bfi

# males and females
Ymale <- subset(Y, gender == 1,
                   select = -c(gender,
                               education))[,1:10]

Yfemale <- subset(Y, gender == 2,
                     select = -c(gender,
                                 education))[,1:10]

# fit model
fit <- ggm_compare_explore(Ymale, Yfemale,
                           iter = 250,
                           type = "continuous",
                           progress = FALSE)
#> Error in .Call("_BGGM_Theta_continuous", PACKAGE = "BGGM", Y = Y, iter = iter +     50, delta = delta, epsilon = eps, prior_only = 0, explore = 1,     start = start, progress = progress): Incorrect number of arguments (8), expecting 10 for '_BGGM_Theta_continuous'


E <- select(fit, post_prob = 0.50)
#> Error in select(fit, post_prob = 0.5): object 'fit' not found

# }