EmpiricalICCfitV1: Subroutine for empirical item characteristic curves

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

Subroutine for empirical item characteristic curves

Description

NOTE: THIS IS A SIMPLIFIED VERSION OF THE FUNCTION FOR EmpiricalICCfit

Usage

EmpiricalICCfitV1(mirtobj, itenum, which.items = NULL, ngroups = 1)

Arguments

mirtobj	An estimated IRT model (of class SingleGroupClass) estimated either using the function "unimirt" or by applying the function "mirt" directly.
itenum	A numeric input denoting which item the plot should be produced for.
which.items	A numeric vector denoting which items should be used to create the total test score. By default all available items are included.
ngroups	The number of groups to split the cohort into in order to produce the empirical points on the curve (the mean total score in each group is plotted against the mean item score). Setting ngroups=1 (the default and the exception to the usual pattern) will create one group for each possible total test score.

Details

The empirical item characteristic curve plots the mean scores on each item for groups with different total scores on the whole test. If the total test scores include the item itself then technically this subroutine calculates the expected relationship against total scores on a parallel test so (for example) a raw total score of zero will not necessarily imply a definite score of zero on the item.

Currently just used as a subroutine within the function EmpiricalICCfit

Value

A list with the following elements.

plot1

A function that translates any vector of scores on form X into equivalent scores on form Y.

modelchartdat

A data frame giving the expected relationship between total score and mean item score based on the IRT model

empiricalchartdat

A data frame giving the empirical results within each group

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