MirtCombine: Combine two estimated IRT models into a single object

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

Combine two estimated IRT models into a single object

Description

This function takes two fitted unidimensional IRT models (fitted using mirt or unimirt) as an input, and combines them into a single object. The function assumes that all parameters are calibrated to a common scale to begin with (e.g. using the function 'MirtStockingLordRecalibrate'). Group parameters are defined by the first object and if common items occur in both objects then parameters from the first object are taken in preference over parameters from the second.

Usage

MirtCombine(mirtobj1, mirtobj2)

Arguments

mirtobj1	An estimated IRT model (of class SingleGroupClass) estimated either using the function unimirt or by applying the function mirt directly. This object defines the ability scale and is given priority in specifying item parameters.
mirtobj2	An estimated IRT model (of class SingleGroupClass) estimated either using the function unimirt or by applying the function mirt directly.

Details

Note that this function will not generally give the same results as concurrent parameter estimation. It's intention is to be used as a pre-cursor for other activities (such as item selection using 'runItemSelectionApp') where it is convenient to store item information in a single object.

Value

A estimated "mirt" object.

Examples

## Not run: 
dat1=mathsdata[1:300,1:8]
dat2=mathsdata[301:400,5:10]
mirt1=unimirt(dat1,"Rasch")
MirtTidyCoef(mirt1)
mirt2=unimirt(dat2,"Rasch")
MirtTidyCoef(mirt2)
mirtcomb=MirtCombine(mirt1,mirt2)
MirtTidyCoef(mirtcomb)

## End(Not run)

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