The cIRT
package (CRAN, GitHub) is home to the implementation of Choice Item Response Theory (cIRT) described by Culpepper and Balamuta (2015). cIRT
jointly models the accuracy of cognitive responses and item choices within a bayesian hierarchical framework.
For more information, please see the full NEWS release below.
cIRT
news file entry for version 1.0.0 (2015-12-01)
Modeling Framework
- Implementation of the hierarchical framework described in “A Hierarchical Model for Accuracy and Choice on Standardized Tests”
- Specifically, a choice inclusive Probit HLM and a Two Parameter Ogive Model.
C++ Functions
- Random Number Generation for the following distributions: Wishart, Inverse Wishart, and Multivariate Normal
- Matrix Centering
- Direct Sum calculation
Data
- Student Performance on Revised Purdue Spatial Visualization Test (Revised PSVT:R) by Yoon, 2011 in
trial_matrix
- The choices students made among items presented to them in
choice_matrix
- The end payout results for students based on their choices in
payout_matrix
- One additional data set exists containing the student’s sex response in
survey_data