A0203
Title: Bayesian biclustering and its application in education data analysis
Authors: Weining Shen - UC Irvine (United States) [presenting]
Abstract: A novel nonparametric Bayesian IRT model is proposed that estimates clusters at the question level while simultaneously allowing for heterogeneity at the examinee level under each question cluster, characterized by the mixture of binomial distributions. The main contribution is threefold. First, the new model is presented and demonstrated to be identifiable under a set of conditions. Second, it is shown that the model can correctly identify question-level clusters asymptotically, and the parameters of interest that measure the proficiency of examinees in solving certain questions can be estimated at a root-n rate (up to a log term). Third, a tractable sampling algorithm is presented to obtain valid posterior samples from the proposed model. Compared to the existing methods, the model reveals the multi-dimensionality of the examinee's proficiency level in handling different types of questions parsimoniously by imposing a nested clustering structure. The proposed model is evaluated via a series of simulations and applied to an English proficiency assessment data set. This data analysis example nicely illustrates how the model can be used by test makers to distinguish different types of students and aid in the design of future tests.
