Package index • irtQ

Getting Started

New to irtQ? Start here with core data structures.

irtQ-package irtQ: irtQ: Unidimensional Item Response Theory Modeling
shape_df(): Create a Data Frame of Item Metadata
shape_df_fipc(): Combine fixed and new item metadata for fixed-item parameter calibration (FIPC)

Item Parameter Estimation

Calibrate item parameters using marginal maximum likelihood (MMLE-EM) and fixed ability methods.

est_irt(): Item parameter estimation using MMLE-EM algorithm
est_mg(): Multiple-group item calibration using MMLE-EM algorithm
est_item(): Fixed ability parameter calibration
getirt(): Extract Components from 'est_irt', 'est_mg', or 'est_item' Objects

Ability Estimation & Scoring

Estimate examinee ability scores from item response data.

est_score(): Estimate examinees' ability (proficiency) parameters
llike_score(): Log-Likelihood of Ability Parameters

Model-Data Fit Evaluation

Assess how well the fitted IRT model describes the observed data.

irtfit(): Traditional IRT Item Fit Statistics
sx2_fit(): S-X2 Fit Statistic
plot(<irtfit>): Draw Raw and Standardized Residual Plots

Differential Item Functioning (DIF)

Detect item bias across examinee groups using residual-based and CATSIB methods.

rdif(): IRT Residual-Based Differential Item Functioning (RDIF) Detection Framework
crdif(): Residual-Based DIF Detection Framework Using Categorical Residuals (RDIF-CR)
grdif(): Generalized IRT residual-based DIF detection framework for multiple groups (GRDIF)
catsib(): CATSIB DIF Detection Procedure
ripd(): Residual-based Item Parameter Drift (RIPD) Detection Framework
pcd2(): Pseudo-count D2 method

Classification Accuracy & Consistency

Evaluate the reliability of cut-score-based pass/fail classifications.

cac_lee(): Classification Accuracy and Consistency Using Lee's (2010) Approach
cac_rud(): Classification Accuracy and Consistency Based on Rudner's (2001, 2005) Approach

Information & Characteristic Functions

Compute and visualize item/test information functions and characteristic curves.

info(): Item and Test Information Function
traceline(): Compute Item/Test Characteristic Functions
plot(<info>): Plot Item and Test Information Functions
plot(<traceline>): Plot Item and Test Characteristic Curves

Data Simulation & Utilities

Simulate item response data and compute supporting quantities.

simdat(): Simulated Response Data
lwrc(): Lord-Wingersky Recursion Formula
gen.weight(): Generate Weights
covirt(): Asymptotic Variance-Covariance Matrices of Item Parameter Estimates
bind.fill(): Bind Fill
bisection(): The Bisection Method to Find a Root
reval_mst(): Recursion-based MST evaluation method
summary(): Summary of Item Calibration Results

Importing External Software Output

Read item parameter estimates from IRT software output files.

bring.flexmirt() bring.bilog() bring.parscale() bring.mirt(): Import Item and Ability Parameters from IRT Software
run_flexmirt(): Run flexMIRT from Within R
write.flexmirt(): Write a "-prm.txt" File for flexMIRT

IRT Model Probability Functions

Core IRT model functions for computing item response probabilities.

drm(): Dichotomous Response Model (DRM) Probabilities
prm(): Polytomous Response Model (PRM) Probabilities (GRM and GPCM)

Datasets

Example datasets bundled with the package.

LSAT6: LSAT6 Data
simCAT_DC: Simulated Single-Item Format CAT Data
simCAT_MX: Simulated Mixed-Item Format CAT Data
simMG: Simulated multiple-group data
simMST: Simulated 1-3-3 MST Panel Data