Nidhi Kohli
-
Royal and Virginia Anderson Professor of Quantitative Methods in Education; quantitative methods in education program coordinator
-
Educational Psychology
166 Education Sciences Bldg.
56 East River Road
Minneapolis, MN 55455 - 612-624-9001
- nkohli@umn.edu
- Download Curriculum Vitae [PDF]
Areas of interest
- Statistical models for longitudinal data (random effects models, latent growth curve models, and growth mixture models)
- Monte Carlo simulation studies
- Model fit evaluation
- Development and validation of new scales/instruments
I am currently accepting doctoral students in the Quantitative Methods in Education (QME) program. Students with research interests that align with mine are encouraged to apply, including students whose research interests fit broadly under the umbrella of the topics above.
PhD, University of Maryland, 2011
MEd, University of Nevada, 2006
I am passionate about the science and application of educational statistics. My expertise spans a range of advanced methodological techniques, including factor analytic models, structural equation models, and various longitudinal data analysis methods, such as latent growth modeling, mixed-effects modeling, and growth mixture modeling. My research is centered on the development and refinement of statistical methodologies for analyzing complex data within education, psychology, and the broader social and behavioral sciences, with a particular focus on longitudinal data—repeated measures collected over time. Through both methodological innovation and interdisciplinary collaboration, I aim to push the boundaries of applied statistics.
A key focus of my work is advancing the understanding of (non)linear relationships among observed and latent variables. I specialize in latent variable methods, particularly nonlinear mixed-effects models and their variations, as well as nonlinear structural equation models. My goal is to contribute to the applied statistics literature, by providing researchers and practitioners with robust theoretical foundations and empirical tools to address critical questions in fields such as education, psychology, health, and human development.
Visit my research website, Longitudinal Methods Development Lab, for more information.
Courses I teach
- EPsy 8282 - Statistical Analysis of Longitudinal Data
- EPsy 8266 - Statistical Analysis Using Structural Equation Methods
Selected publications. Complete list available at Experts@Minnesota and Google Scholar
*Indicates current and former students mentored or supervised by Dr. Kohli.
Davison, M. L., Chung, S., Kohli, N., & Davenport, E. C. (in press, 2024). A multidimensional model to facilitate within person comparison of attributes. Psychometrika. DOI: https://doi.org/10.1007/s11336-023-09946-1
*Choi, S., McMaster, K., Kohli, N., Shanahan, E., Birinci, S., An, Jechun., Duesenberg, M., & Lembke, E. (in press, 2024). Longitudinal effects of data-based instructional changes for students with intensive learning need: A piecewise linear-linear mixed effects modeling approach. Journal of Educational Psychology. DOI: https://doi.org/10.1037/edu0000853
*Rohloff, C. T., Kohli, N., & Lock, E. F. (2024). Identifiability and estimability of Bayesian linear and nonlinear crossed random effects models. British Journal of Mathematical & Statistical Psychology, 77(2), 375–394.
Gunderson, J., Symons, F., Kohli, N., Grzadzinski, R., Burrows, C., Estes, A. M., Dager, S., Piven, J., & Wolff, J. (2024). Longitudinal analysis of sensory responsivity from infancy to school age in children at high and low familial likelihood for autism. Journal of Child Psychology and Psychiatry (JCPP) Advances, e12227. DOI: https://doi.org/10.1002/jcv2.12227
*Peralta, Y., Kohli, N., Kendeou, P., Davison, M. L., & Lock, E. F. (in press, 2023). Modeling the interrelation of reading and mathematics achievement trajectories: Is their development intertwined? Reading and Writing. DOI: https://doi.org/10.1007/s11145-023-10442-2
*Zhang, Z., *Rohloff, C. T., & Kohli, N. (2023). Model fit indices for random effects models: Translating model fit ideas from latent growth curve models. Structural Equation Modeling: A Multidisciplinary Journal, 30(5), 822–830.
*Rohloff, C. T., Kohli, N., & Chung, S. (2023). The impact of functional form complexity on model overfitting for nonlinear mixed-effects models. Multivariate Behavioral Research, 58(4), 723–742.