Poisson regression for modeling count and frequency outcomes in trauma research

Authors

  • David R. Gagnon,

    Corresponding author
    1. Boston University School of Public Health, and Massachusetts Veterans Epidemiology Research, and Information Center, VA Boston Healthcare System, Boston, MA
    • Massachusetts Veterans Epidemiology and Research Information Center, VA Boston Healthcare System (151-MAV), 150 South Huntington Avenue, Boston, MA 02130
    Search for more papers by this author
  • Susan Doron-LaMarca,

    1. Behavioral Science Division, National Center for PTSD, VA Boston Healthcare System, and Boston University School of Medicine, Boston, MA
    Search for more papers by this author
  • Margret Bell,

    1. Military Sexual Trauma Support Team, Department of Veterans Affairs Office of Mental Health Services, and Women's Health Sciences Division, National Center for PTSD, VA Boston Healthcare System, Boston, MA
    Search for more papers by this author
  • Timothy J. O'Farrell,

    1. Families and Addiction Program, Department of Psychiatry, Harvard University Medical School, and VA Boston Healthcare System, Brockton, MA
    Search for more papers by this author
  • Casey T. Taft

    1. Behavioral Science Division, National Center for PTSD, VA Boston Healthcare System, and Boston University School of Medicine, Boston, MA
    Search for more papers by this author

Abstract

The authors describe how the Poisson regression method for analyzing count or frequency outcome variables can be applied in trauma studies. The outcome of interest in trauma research may represent a count of the number of incidents of behavior occurring in a given time interval, such as acts of physical aggression or substance abuse. Traditional linear regression approaches assume a normally distributed outcome variable with equal variances over the range of predictor variables, and may not be optimal for modeling count outcomes. An application of Poisson regression is presented using data from a study of intimate partner aggression among male patients in an alcohol treatment program and their female partners. Results of Poisson regression and linear regression models are compared.

Ancillary