Dr. Victoria Savalei is a Professor in the Department of Psychology. At present she is continuing work on the new estimation method for incomplete data, called the two-stage (TS) method.

I’m a quantitative psychologist with primary research interests in structural equation modeling (SEM)–a powerful statistical modeling tool that allows psychologists to test complicated theories involving multiple observed and latent variables. SEM subsumes other statistical techniques such as regression, path analysis, and factor analysis. One benefit of SEM is that it provides estimates of the relationships between the latent factors controlling for measurement error. Another benefit of SEM is that it produces a test of fit for the entire model. The increasing popularity of SEM has created a need for new developments that are better suited for the types of data that many psychologists have: namely, data that are far from “ideal” but are instead nonnormally distributed, contain missing values, are categorical in nature (e.g., Likert items), or constitute a relatively small sample. One theme of my research has been to develop and evaluate new methods for the SEM analysis of data with one or more of these characteristics, particularly when it comes to the assessment of exact and approximate fit of SEM models. Another theme of my research has been to critically evaluate the existing “rites and rituals” of SEM analyses, to offer new guidelines, and to popularize promising new developments. Recently, I have also become interested in best statistical practices in SEM, particularly in light of the replicability crisis that has been rocking the field of psychology and other behavioral and biomedical fields; this interest has generated several ongoing research projects.

Zhang, X., & Savalei, V. (2022). New computations for RMSEA and CFI following FIML and TS estimation with missing data. Psychological Methods. Advance online publication. http://dx.doi.org/10.1037/met0000445

Savalei, V., & Rosseel, Y. (2022). Computational options for standard errors and test statistics with incomplete normal and nonnormal data. Structural Equation Modeling, 29(2), pp. 163-181. https://doi.org/10.1080/10705511.2021.1877548

Chen, L., & Savalei, V. (2021). Three sample estimates of fraction of missing information from full information maximum likelihood. Frontiers in Psychology, 12. https://doi.org/10.3389/fpsyg.2021.667802

Savalei, V. (2021). Improving fit indices in structural equation modeling with categorical data. Multivariate Behavioral Research, 56(3), 390-407. doi: 10.1080/00273171.2020.1717922

Chen, L., Savalei, V., & Rhemtulla, M. (2020). Two-stage maximum likelihood approach for item-level missing data in regression. Behavior Research Methods, 52, 2306-2323. doi: 10.3758/s13428-020-01355-x

Zhang, X., & Savalei, V. (2020). Examining the effect of missing data on RMSEA and CFI under the normal theory full-information maximum likelihood. Structural Equation Modeling, 27, 219-239. doi: 10.1080/10705511.2019.1642111

Savalei, V., & Reise, S. P. (2019). Don’t Forget the Model in Your Model-based Reliability Coefficients: A Reply to McNeish (2018). Collabra: Psychology, 5(1), 36. doi: http://doi.org/10.1525/collabra.247

Zhang, X., Tse, W-Y., & Savalei, V. (2019). Improved properties of the Big Five Inventory and the Rosenberg Self-Esteem Scale in the Expanded format relative to the Likert format. Frontiers in Psychology, 10:1286. doi:10.3389/fpsycg.2019.01286

Savalei, V. (2019). A comparison of several approaches for controlling measurement error in small samples. Psychological Methods, 24, 352-370. doi: 10.1037/met0000181

For a complete list of publications, visit the lab website.