Davood Tofighi

I am interested in developing and examining multivariate statistical techniques applied to the modeling of psychological data. One of my research interests is mediation analysis, which studies causal modeling of the effect of a treatment (e.g., prevention program) on an outcome (e.g., substance use) achieved by targeting and changing one or more intervening (mediating) variables (e.g., peer drug use norms). The application of mediation analysis has become increasingly popular in various areas of research such as organizational behavior, drug and alcohol use prevention, neuroscience, and epidemiology. Currently, I am working on the application of Bayesian and frequentist methods in mediation analysis while developing a software package in R to implement the techniques. In addition, I am interested in multilevel and longitudinal analysis used to analyze data gathered from intact groups of individuals or repeated measures from the same individuals over time. An important issue in multilevel analysis is the application of different centering strategies on interpretation of regression coefficients. I have also worked on growth mixture modeling, which is used to model the unobserved groups (latent classes) of individuals that share a common growth trajectory over time.

• American Psychological Association (Division 5)

• Tofighi, D., MacKinnon, D. P., & West, S. G. (2009). A general method to derive covariances between parameter estimates in mediation models [abstract]. Multivariate Behavioral Research, 44, 855.
• Tofighi, D., MacKinnon, D. P., & Yoon M. (2009). Covariances between regression coefficient estimates in a single mediator model. British Journal of Mathematical and Statistical Psychology, 62, 457-484.
• Enders, C.K., & Tofighi, D. (2008). The impact of misspecifying class-specific residual variances in growth mixture models. Structural Equation Modeling: A Multidisciplinary Journal, 15(1), 75-95.
• Enders, C.K., & Tofighi, D. (2007). Centering predictor variables in cross-sectional multilevel models: A new look at an old issue. Psychological Methods, 12(2), 121-138.
• Tofighi, D., & Enders, C.K. (2007). Identifying the correct number of classes in growth mixture models. In G. R. Hancock & K. M. Samuelsen (Eds.), Advances in latent variable mixture models (pp. 317-341). Greenwhich, CT: Information Age.
• Tofighi, D., & Enders, C.K. (2007), The harmonic mean. In Encyclopedia of measurement and statistics (Vol. 2, pp. 425-426). Newbury Park, CA: Sage.