MirtSubset: Create a mirt object based on a subset of items in another...

In CambridgeAssessmentResearch/unimirt: Applications of Unidimensional IRT using the R Package 'mirt'

Create a mirt object based on a subset of items in another one

Description

This function takes a fitted unidimensional IRT model (fitted using mirt or unimirt) as an input, and creates a smaller one based on a particular subset of items. This may be useful to enable the shiny apps to focus upon a particular subsection of items. Note that the item parameters are NOT re-estimated. This function is simply intended to allow users to zoom in on results for particular sets of items. For example this might be useful to help produce a Wright Map based on a subset of the items.

Usage

MirtSubset(mirtobj, which.items)

Arguments

mirtobj	An estimated IRT model (of class SingleGroupClass) estimated either using mirt or unimirt.
which.items	an integer vector indicating which items to include in the reduced object.

Details

Note that although the item parameters are unchanged in this process. Fit statistics (or anything else dependent upon producing ability estimates as an intermediate step) will be affected by focussing on a subset of items.

Value

A estimated "mirt" object.

Examples

## Not run: 
mirt1=unimirt(mathsdata,"Rasch")
MirtTidyCoef(mirt1)
mirt2=MirtSubset(mirt1,c(1,3,5,10))
MirtTidyCoef(mirt2)

## End(Not run)

CambridgeAssessmentResearch/unimirt documentation built on June 10, 2025, 6:03 a.m.