S. Natasha Beretvas
Professor & Associate Dean for Research and Graduate Studies
Office & Hours
Office: SZB 538E
Tuesdays 2-3:30 PM for enrolled students, and by appointment
Courses of Instruction
EDP 371 Introduction to Statistics
Correlation and Regression
Advanced Statistical Modeling
EDP 380E Fundamental Statistics
The University of Texas at Austin
1912 Speedway, Stop D5800
Austin, TX 78712-1289
download vita (pdf)
Dr. Beretvas is primarily interested in the evaluation and innovative application of psychometric and statistical models. Her research involves the evaluation of models using simulation studies and application using real data sets. She also examines multilevel modeling with a focus on extensions to the conventional multilevel model in order to handle student mobility and other sources of data structure complexities. Dr. Beretvas utilizes meta-analytic techniques, particularly the synthesis of single-case research design results.
BS, Duke University, 1989
MEd, University of Washington, 1997
PhD, University of Washington, 2000
Wolff Smith, L. J., Beretvas, S. N. (2014). The impact of using incorrect weights with the multiple membership random effects model. Methodology: European Journal of Research Methods for the Behavioral and Social Sciences, 10(1), 31-42. DOI: 10.1027/1614-2241/a000066
Whittaker, T. A., Beretvas, S. N., & Falbo, T. (2014). Dyadic curve-of-factors model: An introduction and illustration of a model for longitudinal nonexchangeable dyadic data. Structural Equation Modeling, 21(2), 303-317.
Beretvas, S. N., & Murphy, D. M. (2013). An evaluation of information criteria use for correct cross-classified random effects model selection. Journal of Experimental Education, 81(4), 429-463.
Li, X., Beretvas, S. N. (2013). Sample size limits for estimating upper-level mediation models using multilevel SEM. Structural Equation Modeling, 20, 241-264.
Beretvas, S. N. (2010). Cross-classified and multiple membership models. In J. Hox & J. K. Roberts (Eds.), The handbook of advanced multilevel analysis (pp. 313-334). New York: NY: Routledge.
John L. and Elizabeth G. Hill Centennial Professorship, 2014
Recipient, College of Education Dean’s Distinguished Teaching Award, 2014
Fellow in the M. K. Hage Centennial Professorship in Education, 2012-2014
Office of Students with Disabilities Recognition, UT-Austin, 2013
Recipient, Vision Award from COE to support development of Dynamic Assessment System for Statistics Courses 2012-2013
Recipient, University of Texas Regents Outstanding Undergraduate Teaching Award, 2009
Current Research Projects and Grants
Institute of Education Sciences: “Multilevel modeling of single-subject experimental data: Handling data and design complexities” (Co-PI, submitted: $260,150).
Institute of Education Sciences: “A research synthesis of the relationships between interest-based motivation and educational outcomes” (Co-PI, submitted: $591,085).
Research Interests and Expertise
Dr. Beretvas is primarily interested in the evaluation and innovative application of psychometric and statistical models. Her research involves the evaluation of models using simulation studies and application using real data sets. She is currently focused on examining extensions to the multilevel model that are intended to handle student mobility and other sources of data structure complexities. Dr. Beretvas also assesses meta-analytic techniques including meta-analysis of results from group comparison studies as well as the synthesis of single-case research design studies’ results.