Description

This package allows the easy generation of ‘Wright Maps’ (named after Ben Wright), also known as item-person maps to display unidimensional and multidimensional assessment results. These maps represent simultaneously the proficiency distribution of respondents and the item difficulty parameters as estimated by a model of the Rasch Family. The package contains several other functions for graphing common IRT statistics.

Additionally, the package contains the CQmodel function, which reads output files created using ConQuest software and creates a set of data frames for easy data manipulation, bundled in a CQmodel object. The wrightMap function can take a CQmodel object as input or it can be used to create Wright Maps directly from data frames of person and item parameters.

Details

The wrightMap function relies on two main inputs: (a) thetas: a vector or matrix of respondent proficiences, and (b) thresholds: a vector or matrix of item thresholds. In the simplest case, say for a unidimensional Rasch model, thetas can be a vector of person proficiencies and thresholds a vector of item difficulties.

To plot multiple dimensions of person proficiency, simply provide them as a matrix were the results for each dimension is stored in a different column, such that for a 3-dimensional model with 1,000 persons, theta is a matrix of 1000 rows and 3 columns.

To plot polytomous items, the thresholds for each level must be passed to the functions through the thresholds matrix, where each row represents an item and each column represents a level. For instance, if the results of a Rating Scale model with 5 response categories and 10 items is being plotted, the thresholds matrix will have 10 rows and 4 columns ( column one represents the thresholds between the 1 and 2 response category, column 2 the threshold between categories 2 and 3, etc.).

Alternatively, wrightMap can read directly the .shw and .eap/.mle/.wle output files from a Conquest analysis, and will automatically generate the thetas and thresholds matrices.

Author(s)

David Torres Irribarra and Rebecca Freund

Maintainer: David Torres Irribarra <dti@berkeley.edu> and Rebecca Freund <rlfreund@berkeley.edu>

References

Andrich, D. (1978). A rating formulation for ordered response categories. Psychometrika, 43(4), 561–573. Masters, G. N. (1982). A Rasch model for partial credit scoring. Psychometrika, 47(2), 149–174. Wilson, M. (2005). Constructing measures: An item response modeling approach. Wright, B. D., \& Stone, M. H. (1979). Best test design. Chicago: Mesa Press.

Examples