group function

Working With Groups

Define or remove the (reference) groups to which the observations belong. methods

group(object, ...)

ungroup(object, ...)

## S4 method for signature 'CompositionMatrix'
group(object, by, verbose = getOption("nexus.verbose"), ...)

## S4 method for signature 'GroupedComposition'
group(object, by, add = FALSE, verbose = getOption("nexus.verbose"), ...)

## S4 method for signature 'GroupedComposition'
ungroup(object)

## S4 method for signature 'GroupedLR'
ungroup(object)

## S4 method for signature 'GroupedCLR'
ungroup(object)

## S4 method for signature 'GroupedALR'
ungroup(object)

## S4 method for signature 'GroupedILR'
ungroup(object)

## S4 method for signature 'GroupedPLR'
ungroup(object)

Arguments

• object: An object (typically, a CompositionMatrix object).
• ...: Further parameters to be passed to internal methods.
• by: A possible value for the groups of object (typically, a character vector). If value is a list, interaction(by) defines the grouping.
• verbose: A logical scalar: should report extra information on progress?
• add: A logical scalar. If TRUE, add to existing groups.

Returns

• group() returns a grouped object of the same sort as object.
• ungroup() returns an ungrouped object of the same sort as object.

Details

Missing values (NA) can be used to specify that a sample does not belong to any group.

Examples

## Data from Aitchison 1986
data("slides")

## Coerce to compositional data
coda <- as_composition(slides, groups = 2)

## Grouping metadata
group_levels(coda)

group_names(coda)

group_indices(coda)

group_rows(coda)

group_length(coda)

group_size(coda)

See Also

Other grouping methods: group_metadata, group_split(), group_subset()

Author(s)

N. Frerebeau