Bayesian Hierarchical Modeling with 3PNO Item Response Models
Year: 2013
Type: article
Abstract: Fully Bayesian estimat ion has been developed for unidimensional IRT models. In this context, prior distributions can be specified in a hierarchical manner so that item hyperparameters are unknown and yet still have their own priors. Th is type of hierarchical modeling is useful in terms of the three-parameter IRT model as it reduces the difficu lty of specifying model hyperparameters that lead to adequate prior distributions. Further, hierarch ical modeling amelio rates the noncovergence problem associated with nonhierarchical models when appropriate prior informat ion is not available. As such, a Fortran subroutine is provided to implement a hierarchical modeling procedure associated with the three-parameter normal og ive model for binary item response data using Gibbs sampling. Model parameters can be estimated with the choice of noninformative and conjugate prior d istributions for the hyperparameters.
Authors: Yanyan Sheng, Todd C. Headrick
Institution: Southern Illinois University Carbondale
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W2150114828
