| grp {irtoys} | R Documentation |
Groups a vector of estimates of the latent variable into a
histogram-like object. Typically invoked by function
itf, unless the user wishes to access some of the
non-default settings.
grp(theta, bin.type = "quant", bin.numb = 10, ref.type = "meds")
theta |
The latent variable estimates to be binned |
bin.type |
One of "autom", "gauss", or "quant". "autom" uses the algorithm of hist(), producing bins with highly variable frequencies. "gauss" and "quant" try to produce groups of roughly equal size. "gauss" assumes a Normal distribution while "quant" is based on the empirical quantiles. Default is "quant" |
bin.numb |
The number of bins (only a suggestion when bin.type="autom") |
ref.type |
The points at which itf will evaluate the IRF. One of "mids" (the mid-point of each bin), "meds" (the median of the values in the bin), or "means" (the mean of the values in the bin). Default is "meds". When "bin.type=autom", "meds" defaults to "mids" |
A list of:
breaks |
The breaks between adjacent bins |
counts |
The number of values in each bin |
ref |
Depending on ref.type, the mids of the bin, or the mean or median of the values in the bin |
Ivailo Partchev
data(Scored) p.2pl <- est(Scored, model="2PL", engine="ltm") th.mle <- mlebme(resp=Scored, ip=p.2pl) gr <- grp(th.mle, bin.numb=7)