Stephen L. Rathbun

Epidemiology & Biostatistics

Curriculum Vitae

Epidemiology & Biostatistics

  • Education

    PhD, Statistics, Iowa State University, 1990

    MS, Statistics, Iowa State University, 1987

    MS, Biology, Florida State University, 1980

    BS, Biology, Florida State University, 1976

  • Areas of Expertise

    Research: ecological momentary assessment, ecological momentary intervention, spatial epidemiology, recurrent behavioral events, mixed effects models, point process models, geostatistics, regional data, smoking, dietary lapse, asthma

    Teaching: introductory biostatistics for public health, spatial epidemiology, multivariate design, consulting, advanced inference

  • Honors, Awards, and Achievements

    Excellence in Research Award, College of Public Health, University of Georgia, 2009

  • Affiliations

    American Statistical Association

  • Course Instruction

    Bios 7010 Introductory Biostatistics

    Bios 8130 Multivariate Design for Public Health

    Bios 8150 Spatial Epidemiology

    Bios 8200 Biostatistical Consulting I

    Bios 8210 Biostatistical Consulting II

    Bios 8310 Asymptotic Biostatistical Inference

    Biostatistical methods are taught through the use of a diverse variety of data from public health and biomedicine. Emphasis is given to the appropriate use of statistical software, understanding the statistical content of the public health literature, the limits of statistical inference, and drawing thorough conclusions from results of statistical analysis.

  • Research Interests

    Dr. Rathbun’s research focuses on the analysis of data collected using Ecological Momentary Assessment, a study design in the behavioral sciences that often uses electronic devices (e.g., cell phones) to collect data on salient behavioral events (e.g., smoking a cigarette), and representative samples of participants’ moods and environments in the every-day environments of study participants. He has developed biostatistical methods for fitting mixed-effects versions of recurrent-events models that may be used to describe variation among subjects in how they respond to their moods and environments. His long-term goal is to develop biostatistical methods for delivering adaptive subject-specific behavioral interventions to improve treatment for smoking cessation, dietary compliance, and asthma.

  • Selected Publications

    Rathbun, S.L., and Shiffman, S. (2016). Mixed effects models for recurrent events data with partially observed time-varying covariates: Ecological momentary assessment of smoking. Biometrics 72, 46-55. NIHMSID 728077

    Rathbun, S.L. (2013). Optimal estimation of Poisson intensity with partially observed covariates. Biometrika 100, 277-281.

    Rathbun, S.L., Song, X., Neustifter, B., and Shiffman, S. (2013). Survival Analysis with Time-Varying Covariates Measured at Random Times by Design. Journal of the Royal Statistical Society, Series C 62, 419-434.

    Neustifter, B., Rathbun, S.L. and Shiffman, S. (2012). Mixed-Poisson point process with partially-observed covariates: ecological momentary assessment of smoking. Journal of Applied Statistics 39, 883-899.

    Shiffman, S., and Rathbun, S.L. (2011). Point process analyses of variations in smoking rate by setting, mood, gender, and dependence. Psychology of Addictive Behaviors 25, 501-510.

    Rathbun, S.L., Shiffman, S., and Gwaltney, C. 2007. Modeling the effects of partially observed covariates on Poisson process intensity.Biometrika 94, 153-165.