jacobian_irtree: Check identifiability of models.

In hplieninger/mpt2irt: Bringing Multinomial Processing Tree Models To Item Response Theory To Investigate Response Styles

Description

Generate random parameter values and test, whether the Jacobian has full rank.

Usage

jacobian_irtree(N, J, revItem = rep(1, J), traitItem = rep(1, J), type,
  fixed.theta = TRUE, rep = 100, betas, theta)

Arguments

N	number of persons
J	number of items
revItem	vector of length J specifying reversed items (1=reversed, 0=regular)
traitItem	vector of length J specifying the underlying traits (e.g., indexed from 1...5). Standard: only a single trait is measured by all items. If the Big5 are measured, might be something like c(1,1,1,2,2,2,...,5,5,5,5)
type	either "2012", "ext", "ext2", or "ext3"
fixed.theta	if TRUE, assumes that mean of theta parameters is assumed to be fixed at zero
rep	number of points in parameter space to check identification
betas	optional matrix with beta parameters
theta	optional matrix with theta parameters (note that the parameters of the first person will be set to to minus the theta-column means if fixed.theta=TRUE)

Examples

# Standard model identified, even without reversed items:
jacobian_irtree(N=6, J=8, revItem=rep(1,8), type=2012, rep=5)

hplieninger/mpt2irt documentation built on May 17, 2019, 4:54 p.m.