kcirt.model(constructMap.ls, qTypes, data = NULL, Y = NULL, mu = 0, mxLambda = NULL,
covEta = 1, covShocks = 1, deltaType=1)
Arguments
constructMap.ls
How the constructs map to the items. A list of vectors, each vector representing a block (question in the instrument); each element of a vector giving the construct index.
qTypes
Is a question to be fully ranked or most/least format. A character vector whose length is the number of blocks. Each element in {"R", "M"}. Note that only accepts 'R' when corresponding block has 3 or 2 items.
data
Data matrix. The number of columns is the number of observational units, the number of rows is the total number of items.
Y
Response cohort matrix, each element in {NA,0,1}.
mu
True item means. A real-valued vector whose length is the total number of items.
mxLambda
True hyperparameters. A real-valued square matrix, or a vector. If vector, mxLambda is assumed to be diagonal (no item crosstalk) – vector is recycled
covEta
True covariance of states. A square, symmetric real-valued matrix.
covShocks
True covariance of shocks. A square, symmetric real-valued matrix.
deltaType
Tell function in what pattern items are compared. Scalar. Directly affects structure of the Delta matrix. Currently one of two integer values. 1 is default. 2 is that implied by Brown and Maydeau-Oliveras.
Value
A kcirt model. A named list of class “kcube.irt.model”.
Author(s)
Dave Zes, Korn/Ferry International
Examples
constructMap.ls <- list(
c(1,2),
c(2,3),
c(1,3)
)
qTypes <- rep("R", length(constructMap.ls))
mod <- kcirt.model(constructMap.ls=constructMap.ls, qTypes=qTypes, mxLambda=NULL)
## view contents
mod