Jodi M. Casabianca
Postdoctoral Fellow
After CMART
Dr. Casabianca was appointed in Fall 2013 as an Assistant Professor, Department of Educational Psychology, Quantitative Methods Program, University of Texas at Austin, Austin TX.
Education
Ph.D., Psychometrics, Fordham University, 2011 M.A., Psychometrics, Fordham University, 2008 M.S., Applied and Mathematical Statistics, Rutgers University, 2004 B.A., Statistics & Psychology, Rutgers University, 2001
Research Interests
My general research interests include psychometrics and educational statistics/measurement. Some specific areas of interest include:
- Latent variable models, including IRT, rating and cognitive diagnosis models;
- IRT parameter estimation and item parameter recovery;
- Longitudinal modeling of ratings and responses;
- Validity and reliability in classroom and teacher assessment;
- Evaluation in education.
Selected Recent/Ongoing Work
Casabianca, J. M., & Junker, B. W. (2015). The Hierarchical Rater Model for Longitudinal Ratings. Submitted for publication.
Casabianca, J. M., & Lewis, C. (2012). Equivalence testing for differential item functioning: Standard and Bayesian approaches. Carnegie Mellon University working paper.
Casabianca, J. M., & Junker, B. W. (September 2012). Estimating latent distributions using loglinear smoothing models. Carnegie Mellon University working paper.
Casabianca, J. M., McCaffrey, D. F., Gitomer, D., Bell, C., Hamre, B. K., & Pianta, R. C. (in press). Effect of observation mode on measures of secondary mathematics teaching. (Click here for Supplemental Material)
Casabianca, J. M., & Lewis, C. (2012). Loglinear smoothing models for the latent trait distribution in the marginal maximum likelihood estimation of 3PL item parameters. Submitted for publication.
Junker, B. W., Casabianca, J. M., & Patz, R. (2012). The hierarchical rater model. Invited chapter for W. J. van der Linden & R. K. Hambleton (Eds.), Handbook of model item response theory. Boca Raton, FL: Chapman & Hall/CRC.
Junker, B. W., & Casabianca, J. M. (2012). Discrete distributions relevant to item response theory. Invited chapter for W. J. van der Linden & R. K. Hambleton (Eds.), Handbook of model item response theory. Boca Raton, FL: Chapman & Hall/CRC.
Junker, B. W., & Casabianca, J. M. (2012). Multivariate normal distributions. Invited chapter for W. J. van der Linden & R. K. Hambleton (Eds.), Handbook of model item response theory. Boca Raton, FL: Chapman & Hall/CRC.
Casabianca, J. M., Xu, X., Jia, Y., & Lewis, C. (2011). Estimation of item parameters when the underlying latent trait distribution of test takers is nonnormal. Submitted for publication.
Casabianca, J. M., Budescu, D. V., Fyffe, D., & Lewis, C. (2010). A comparison of classification techniques for diagnosis in an Alzheimer's study. Multivariate Behavioral Research, 45, 1021. (Abstract).
Hebert, P. L., Sisk, J. E., Wang, J. J., Tuzzio, L., Casabianca, J. M., Chassin, M. R., Horowitz, C., & McLaughlin, M. A. (2008). Cost-effectiveness of nurse-led disease management for heart failure in an ethnically diverse urban community. Annals of Internal Medicine, 149, 540-548.
von Davier, A. A., Holland, P. W., Livingston, S. A., Casabianca, J. M., Grant, M. C., & Martin, K. (2006). An evaluation of the kernel equating method: A special study with pseudotests constructed from real test data. (Research Report 06-02), Princeton, NJ: Educational Testing Service.
Moses, T., von Davier, A. A., & Casabianca, J. M. (2004). Loglinear smoothing: An alternative numerical approach using SAS. (Research Report 04-27), Princeton, NJ: Educational Testing Service.
Bischof, D. L., Baum, D., Casabianca, J. M., Morgan, R., Rabiteau, K., & Tateneni K. (2004). Validating AP modern foreign language examinations through college comparability studies. Foreign Language Annals, 37, 616-622.
Projects
Longitudinal Hierarchical Rater Models (HRMs): I am extending the HRM framework to include multiple timepoints. Preliminary work uses an autoregressive time series model of order 1 to treat time ordinally. The goal of this project is to make the HRM approach available to performance and rated assessment situations such as teacher/classroom assessments that are completed multiple times over the school year.
Estimating latent distributions with loglinear models: In this research I am making theoretical generalizations about the use of loglinear models and smoothing models for estimating latent histograms in a variety of contexts. The goal is to define a framework for different approaches to specifying latent histograms and using loglinear (smoothing) models to unify the framework.
Comparison of modes of classroom assessment: I am working with a multisite team to evaluate/compare video and live ratings in their differenial sources of variation on a secondary school teacher assessment tool. We compare modes using a generalizability study (and D Studies) to evaluate/compare the sources of variance and reliability under different scoring design scenarios (number of raters, number of ratings, lessons)
Evaluation of differentiated professional development (PD): I am working on an initiative led by RAND to evaluate different HR reforms on teacher effectiveness and student achievement. My specific responsibility is to evaluate the impact of teacher PD taking into account the motivating mechanisms for selection into various possible PD experiences.
Contact Information
The University of Texas at Austin
Educational Psychology Department
jcasabianca@austin.utexas.edu