seqivardur: Variance of spell durations in individual sequences

In TraMineR: Trajectory Miner: a Sequence Analysis Toolkit

Variance of spell durations in individual sequences

Description

Variance of spell durations of individual state sequences.

Usage

seqivardur(seqdata, type=1, with.missing=FALSE)

## S3 method for class 'seqivardur'
print(x, stat='var', ...)

Arguments

seqdata	a state sequence object (stslist) as returned by seqdef.
type	either 1 or 2. The default type=1 ignores non visited states. Type 2 takes into account the 0-time spent in non-visited states (see Details).
with.missing	logical: should non-void missing values be treated as a regular state? If FALSE (default) missing values are ignored.
x	an outcome of seqivardur.
stat	string or vector of strings. Duration statistic to be printed. Either 'mean' (mean duration), 'std' (standard deviation), 'var' (variance), 'vmax' (maximum variance for number of spells), or 'all'. Default is 'var'.
...	further arguments such as digits passed to the next print method.

Details

The returned variance is a population variance, i.e. the sum of squares divided by the number of terms.

When type=1, this is the variance of the observed spells in the sequence. When type=2, in addition to the observed spells one spell of length 0 is considered for each non-visited state. The mean duration is computed the same way.

Value

A numeric vector with the variance of spell duration of each sequence.

The returned object has two attributes:

vmax	the maximum value that the variance of each sequence could reach given its number of spells.
meand	the mean spell duration of each sequence.

Author(s)

Gilbert Ritschard

References

Ritschard, G. (2021), "Measuring the nature of individual sequences", Sociological Methods and Research, \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1177/00491241211036156")}.

See Also

seqdur, seqindic

Examples

sq.dat <- c('AAAA','AAAC','ABC','ABAA','AC')
sq <- seqdef(seqdecomp(sq.dat, sep=''), right=NA)

seqivardur(sq, type=1)
seqivardur(sq, type=1, with.missing=TRUE)
vd2 <- seqivardur(sq, type=2)
print(vd2, stat='all')
vd2m <- seqivardur(sq, type=2, with.missing=TRUE)
print(vd2m, stat=c('var','vmax'))

TraMineR documentation built on Sept. 19, 2023, 1:07 a.m.