Skip to Main Content

College Overview

* (COPH C Overview faculty)

Matthew Valente

Matthew Valente, PhD

Assistant Professor

Contact Info

Education

  • PhD, Arizona State University, 2018
  • MA, Arizona State University, 2015
  • BS, University of North Florida, 2010

Discipline

Quantitative Research Methods

Specialization

  • Causal Inference
  • Statistical Mediation Analysis
  • Preventive Interventions

Biography

Matthew received his PhD from Arizona State University in 2018. He has two main areas of research. First, his research consists of bridging the gap between modern causal mediation methods and currently accepted statistical mediation methods in the health and social sciences. Second, his research involves developing and evaluating statistical mediation analysis methods in the context of longitudinal data and preventive interventions. In addition to his focal research, Matthew has assisted with data analytic issues on several federally funded projects evaluating effects of health intervention programs. Together with Dr. Judith Rijnhart, Dr. Valente runs the Causal Inference in Public Health Research (CIPHR) lab. This lab is focused on the evaluation and application of causal inference methods in public health research. Drs. Valente and Rijnhart hold bi-weekly lab meetings in which causal inference topics are discussed. The students in the CIPHR lab have a wide range of backgrounds and skill levels, including undergraduate students, master-level students, and doctoral-level students with concentrations in epidemiology or biostatistics. Students interested in joining the CIPHR lab can send an email to Dr. Valente (mjvalente@usf.edu) and/or Dr. Rijnhart (jrijnhart@usf.edu).

Research Interests

  • Applying advanced statistical methodology aimed at improving health-related outcomes.
  • Developing and evaluating modern causal inference methods for mediation analysis including moderated-mediation analysis.
  • Developing and evaluating causal mediation analysis methods in the context of randomized experiments with longitudinal data.
  • Bridging the gap between new cutting-edge causal mediation methods and currently accepted statistical mediation methods in health-related research.