1st Edition
Handbook of Item Response Theory Volume 2: Statistical Tools
Drawing on the work of internationally acclaimed experts in the field, Handbook of Item Response Theory, Volume Two: Statistical Tools presents classical and modern statistical tools used in item response theory (IRT). While IRT heavily depends on the use of statistical tools for handling its models and applications, systematic introductions and reviews that emphasize their relevance to IRT are hardly found in the statistical literature. This second volume in a three-volume set fills this void.
Volume Two covers common probability distributions, the issue of models with both intentional and nuisance parameters, the use of information criteria, methods for dealing with missing data, and model identification issues. It also addresses recent developments in parameter estimation and model fit and comparison, such as Bayesian approaches, specifically Markov chain Monte Carlo (MCMC) methods.
Basic Tools
Logit, Probit, and Other Response Functions
James H. Albert
Discrete Distributions
Jodi M. Casabianca and Brian W. Junker
Multivariate Normal Distribution
Jodi M. Casabianca and Brian W. Junker
Exponential Family Distributions Relevant to IRT
Shelby J. Haberman
Loglinear Models for Observed-Score Distributions
Tim Moses
Distributions of Sums of Nonidentical Random Variables
Wim J. van der Linden
Information Theory and Its Application to Testing
Hua-Hua Chang, Chun Wang, and Zhiliang Ying
Modeling Issues
Identification of Item Response Theory Models
Ernesto San MartÃn
Models with Nuisance and Incidental Parameters
Shelby J. Haberman
Missing Responses in Item Response Modeling
Robert J. Mislevy
Parameter Estimation
Maximum-Likelihood Estimation
Cees A. W. Glas
Expectation Maximization Algorithm and Extensions
Murray Aitkin
Bayesian Estimation
Matthew S. Johnson and Sandip Sinharay
Variational Approximation Methods
Frank Rijmen, Minjeong Jeon, and Sophia Rabe-Hesketh
Markov ChainMonte Carlo for Item Response Models
Brian W. Junker, Richard J. Patz, and Nathan M. VanHoudnos
Statistical Optimal Design Theory
Heinz Holling and Rainer Schwabe
Model Fit and Comparison
Frequentist Model-Fit Tests
Cees A. W. Glas
Information Criteria
Allan S. Cohen and Sun-Joo Cho
Bayesian Model Fit and Model Comparison
Sandip Sinharay
Model Fit with Residual Analyses
Craig S. Wells and Ronald K. Hambleton
Biography
Wim J. van der Linden is a distinguished scientist and director of research innovation at Pacific Metrics Corporation. He is also a professor emeritus of measurement and data analysis at the University of Twente. He is a past president of the Psychometric Society and National Council on Measurement in Education (NCME) and a recipient of career achievement awards from NCME, Association of Test Publishers (ATP), and American Educational Research Association (AERA). His research interests include test theory, computerized adaptive testing, optimal test assembly, parameter linking, test equating, and response-time modeling as well as decision theory and its application to problems of educational decision making. Dr. van der Linden earned a PhD in psychometrics from the University of Amsterdam.