Bayesian Estimation and Model Choice in Item Response Models

By Sujit Kumar Sahu. 2002

89 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/0d9e18186f643cccf02061ba3e5bfb7aa22143fd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Estimation of Compensatory and Noncompensatory Multidimensional Item Response Models Using Markov Chain Monte Carlo (2003, methodology): “Various criteria can be used in the context of MCMC to compare item response models (Sahu, 2002).”
A Bayesian Semiparametric Latent Variable Model for Mixed Responses (2007, unknown): “Among others, Patz and Junker (1999a, 1999b) demonstrate that MCMC techniques are particularly well suited for complex models with IRT assumptions, Sahu (2002) considers model choice in item response models, and Lu and Wang (2006) suggest a hierarchical Bayesian framework for ideal point estimatio”
IRT Model Selection Methods for Dichotomous Items (2007, background): “As Lin and Dayton (1997), Lord (1975), and Sahu (2002) note, however, asymptotic estimates of item parameters may not always be available, in which case neither AIC nor BIC is appropriate.”
Performances of LOO and WAIC as IRT Model Selection Methods (2017, methodology): “In the Bayesian IRT literature, one of the most popular model comparison methods is DIC.”
Ordinal Data Modeling (2000, methodology): “Details of this fitting algorithm are provided in Sahu (1997).”
Model Selection Methods for Mixture Dichotomous IRT Models (2009, methodology): “Sinharay et al. (2006) introduced a number of discrepancy measures for IRT models, one of which, posterior predictive checks based on item pair odds ratios (OR), was found to be an effective tool for detecting lack of fit in standard IRT models. Li, Bolt, and Fu (2006) also found the OR to be a more”
To Bayes or Not to Bayes, From Whether to When: Applications of Bayesian Methodology to Modeling (2004, methodology): “selves and often illustrate them with the more complex models such as the 3PL, whichhasbecomemoreofanexample thanahook for thepresentationof theestimation results (e.g., Patz & Junker, 1999a, 1999b; Sahu, 2002).”
A skew item response model (2006, methodology): “muz[i,j]<-m[i,j]-delta[j]*V[i,j] Zs[i,j] ~ dnorm(muz[i,j],preczs[j])I(lo[y[i,j]+1],up[y[i,j]+1]) V[i,j] ~ dnorm(0,1)I(0,) } } #priors for item parameters for (j in 1:k) { #A prior: Sahu (2002) a[j] ~ dnorm(1,2)I(0,) b[j] ~ dnorm(0,0.5) delta[j] ~ dunif(-1,1) #B prior : Sahu (2002) #a[j] ~ dnorm(1,2)”