Paper Summary

Direct link:

Joint Modeling Response Time and Response Accuracy

Thu, April 16, 12:00 to 1:30pm, Sheraton, Floor: Fourth Level, Chicago VI&VII


During the student testing, response time (RT) and response accuracy (RA) provide rich information on both student’s performance and behavior. Joint estimation could improve accuracy of estimates of student achievement ability and speediness. Until today, most published parameter estimations method used in joint modeling is Bayesian approach with Markov Chain Monte Carlo (MCMC) using Winbugs. The powerful restricted pseudo-likelihood method (RPLM) that is implemented in Proc GLIMMIX in SAS software has not been explored in this context. The purpose of this study is to compare the estimation accuracy and efficiency of joint modeling response time and response accuracy using Bayesian and restricted pseudo-likelihood methods.