Health and behavioral cancer researchers require highly reliable, objective, and methodologically founded measurement instruments, accurate scaling of subjects on important health-related attributes, and statistically sound procedures for evaluating differences among groups (such as treatment vs control) and change across time. Item response theory (IRT) provides a powerful modeling framework for achieving these goals via the measurement of latent attributes that are only indirectly measured by observable data. Unfortunately, there is a massive lack of user-friendly IRT software that allows for a straightforward computation of a variety of IRT models in daily research applications.
The aim of this project is the development of flexible, user-friendly IRT software especially suited for researchers in the health sciences. This software will run on multiple platforms and cover a broad spectrum of IRT models such as classical binary models (Rasch, 1-PL, 2-PL, 3-PL), classical polytomous models (GRM, RSM, PCM, NRM), as well as up-to-date approaches such as models with covariates (mixed-effects models) and multidimensional models that are highly relevant for health related research questions. The generalized models enable analysis of longitudinal and multilevel data, as well as examination of treatment group effects on a scale. Multidimensional models overcome the sometimes rather restrictive assumptions that require analysis of only one attribute at a time. From a technical point of view, the program will offer numerous statistical estimation approaches for item and person parameters such as MML, nonparametric MML, fully nonparametric models, MCMC, Bayesian EAP, weighted likelihood, etc. Once the parameters are estimated, a researcher can evaluate the model by means of a large set of model tests and fit indices. Numerous interactive high- level plots will allow for a customizable visualization of the results, and an XML export will assure that tables and figures are publication quality. A special emphasis in terms of user-friendliness is the use of a JAVA based graphical user interface (GUI) that will be consistent across a variety of computing platforms. Throughout the IRT modeling workflow, a researcher will be supported by context-sensitive dialog boxes. Experienced IRT scholars will have the option to refine their models using an intuitive IRT command language. The software package will be supported by a comprehensive online platform (Wiki) including technical explanations, a user's guide, model and data examples, a news section, a discussion board, a FAQ section, and other features.

Public Health Relevance

Modern IRT measurement techniques by means of a user-friendly IRT software lead to a reliable and objective construction of health scales, to shorter adaptive or fixed scales for measuring more in a less amount of time, to a finer understanding of change in epidemiology studies and clinical trials, and to a sensitive examination of cross-cultural differences in trait structure and response sets. This software vastly improves the understanding of public health and quality of life.

Agency
National Institute of Health (NIH)
Institute
National Cancer Institute (NCI)
Type
Small Business Innovation Research Grants (SBIR) - Phase II (R44)
Project #
5R44CA137841-03
Application #
7797621
Study Section
Special Emphasis Panel (ZRG1-HOP-E (10))
Program Officer
Weber, Patricia A
Project Start
2008-09-30
Project End
2012-03-31
Budget Start
2010-04-01
Budget End
2012-03-31
Support Year
3
Fiscal Year
2010
Total Cost
$391,507
Indirect Cost
Name
Multivariate Software, Inc.
Department
Type
DUNS #
959579061
City
Encino
State
CA
Country
United States
Zip Code
91436
Jennrich, Robert I; Bentler, Peter M (2011) Exploratory Bi-factor Analysis. Psychometrika 76:537-49
Cheng, Ying; Yuan, Ke-Hai (2010) THE IMPACT OF FALLIBLE ITEM PARAMETER ESTIMATES ON LATENT TRAIT RECOVERY. Psychometrika 75:280-291
Reise, Steven P; Moore, Tyler M; Haviland, Mark G (2010) Bifactor models and rotations: exploring the extent to which multidimensional data yield univocal scale scores. J Pers Assess 92:544-59