TraMineRextras (version 0.6.8)

seqrep.grp: Finding representative sets by group and their quality statistics.

Description

This function determines representative sequences by group and returns the representatives by group and/or the quality statistics of the representative sets. The function is a wrapper for the TraMineR seqrep function.

Usage

seqrep.grp(seqdata, group = NULL, diss = NULL, ret = "stat",
    with.missing = FALSE, mdis, ...)

Value

If ret="stat", a list with the quality statistics for the set of representatives of each group.

If ret="rep", a list with the set of representatives of each group. Each element of the list is an object of class stslist.rep returned by seqrep.

If ret="both", a list with the two previous outcomes.

Arguments

seqdata

state sequence object as defined by seqdef.

group

group variable. If NULL a single group is assumed.

diss

dissimilarity matrix. If NULL the “LCS” dissimilarity matrix is computed.

ret

What should be returned? One of "stat" (default), "rep" or "both".

with.missing

Logical. When diss = NULL. Are there missing values in the sequences? Default is FALSE.

mdis

Deprecated. Use diss instead.

...

additional arguments passed to seqrep .

Author

Gilbert Ritschard

Details

The function is a wrapper for running seqrep on the different groups defined by the group variable.

When diss = NULL, seqdist is used to compute the dissimilarities.

See Also

seqrep

Examples

data(biofam)
biofam <- biofam[1:100,]
biofam.lab <- c("Parent", "Left", "Married", "Left+Marr",
"Child", "Left+Child", "Left+Marr+Child", "Divorced")
biofam.short <- c("P","L","M","LM","C","LC","LMC","D")
biofam.seq <- seqdef(biofam[,10:25], alphabet=0:7, 
  states=biofam.short, labels=biofam.lab)
dist <- seqdist(biofam.seq, method="HAM")

seqrep.grp(biofam.seq, group=biofam$plingu02, diss=dist, coverage=.2, pradius=.1)
seqrep.grp(biofam.seq, group=biofam$plingu02, diss=dist, ret="rep", coverage=.2, pradius=.1)

## sequences with missing values
data(ex1)
sqex1 <- seqdef(ex1[,1:13])
nrow(ex1)
gp <- rep(1,7)
gp[5:7] <- 2
seqrep.grp(sqex1, group=gp, method="LCS", ret="rep", 
  coverage=.2, pradius=.1, with.missing=TRUE)