American Statistical Association
Cognitive assessment is a growing area in psychological and educational measurement, where subjects' responses are collected to assess mastery of skills in educational measurements or presence of mental disorders in psychological measurements. Such (latent) characteristics (mastery of skills and presence of disorders) are usually called attributes. A key issue is the correct identification of the attributes associated with each item (such as exam problems or survey questions). Such a relationship is usually described by the so-called Q-matrix. In this talk, we address the estimation problem of the Q-matrix based on the subjects’ responses under stylized diagnostic classification models. We apply the proposed method to several educational testing examples including standard language testing and a midterm exam from a course taught by me last semester.
Dr. Jingchen Liu is currently an Assistant Professor in the Department of Statistics at Columbia University. Jingchen received his Ph.D. in Statistics from Harvard University in 2008. His research interest consists of Bayesian modeling especially for missing data, multiple imputation, applied probability, and Monte Carlo methods.
|Date:||Tuesday, February 21, 2012|
|Time:||3:30 - 4:30 P.M.|
New York State Psychiatric Institute
1051 Riverside Drive
6th Floor Multipurpose Room (6602)
New York, New York