Recovery of Item Parameters in the Nominal Response Model: A Comparison of Marginal Maximum Likelihood Estimation and Markov Chain Monte Carlo Estimation

87 citations recorded by the source corpus.

How researchers see this paper

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

A Mixture Model Analysis of Differential Item Functioning (2005, methodology): “MCMC estimation algorithms are receiving increasing attention in IRT (see, for example, Baker, 1998; Bolt, Cohen, & Wollack, 2001, 2002; Kim, 2001; Patz & Junker, 1999a, 1999b; Wollack et al., 2002).”
The Role of Extended Time and Item Content on a High–Stakes Mathematics Test (2005, unknown): “Theparametersoftheresultingmodelwerees-timated using a Markov Chain Monte Carlo (MCMC) algo-rithm (see, e.g., Baker, 1998; Bolt, Cohen, & Wollack, 2001, 2002; Patz & Junker, 1999a, 1999b; Wollack, Bolt, Cohen, & Lee, 2002).”
Addressing Score Bias and Differential Item Functioning Due to Individual Differences in Response Style (2009, methodology): “The parameter recovery results in terms of root mean square error (RMSE) were found to be on the order of that observed using more traditional IRT software packages (e.g., MULTILOG) considered by Wollack et al. (2002).”
Recovery of Graded Response Model Parameters (2012, methodology): “Wollack et al. (2002) reported that estimation of NRM parameters with 300 persons and 10 items took 4 hrs and 10 mins on a Note: L = test length; MML = marginal maximum likelihood; EAP = expected a posteriori; MCMC = Markov chain Monte Carlo; MAP = maximum a posteriori.”