Binary regression: Total gain in positive and negative predictive values

Authors

  • Jens Klotsche,

    Corresponding author
    1. Center of Clinical Epidemiology and Longitudinal Studies (CELOS), Technische Universitaet Dresden, Dresden, Germany
    • Institute of Clinical Psychology and Psychotherapy, Technische Universitaet Dresden, Dresden, Germany
    Search for more papers by this author
  • Dietmar Ferger,

    1. Department of Mathematics, Technische Universitaet Dresden, Dresden, Germany
    Search for more papers by this author
  • David Leistner,

    1. Department of Medicine III, Cardiology, Goethe-University Frankfurt, Frankfurt, Germany
    Search for more papers by this author
  • Lars Pieper,

    1. Institute of Clinical Psychology and Psychotherapy, Technische Universitaet Dresden, Dresden, Germany
    2. Center of Clinical Epidemiology and Longitudinal Studies (CELOS), Technische Universitaet Dresden, Dresden, Germany
    Search for more papers by this author
  • Andreas M. Zeiher,

    1. Department of Medicine III, Cardiology, Goethe-University Frankfurt, Frankfurt, Germany
    Search for more papers by this author
  • Hans-Ulrich Wittchen,

    1. Institute of Clinical Psychology and Psychotherapy, Technische Universitaet Dresden, Dresden, Germany
    2. Center of Clinical Epidemiology and Longitudinal Studies (CELOS), Technische Universitaet Dresden, Dresden, Germany
    Search for more papers by this author
  • Juergen Rehm

    1. Institute of Clinical Psychology and Psychotherapy, Technische Universitaet Dresden, Dresden, Germany
    2. Center of Clinical Epidemiology and Longitudinal Studies (CELOS), Technische Universitaet Dresden, Dresden, Germany
    3. Public Health and Regulatory Policy Section, Centre for Addiction and Mental Health, Toronto, Canada
    Search for more papers by this author

Corresponding author: e-mail: klotsche@psychologie.tu-dresden.de, Phone: +49-351-463-37462, Fax: +49-351-463-36984

Abstract

Models that predict disease incidence or disease recurrence are attractive for clinicians as well as for patients. The usefulness of a risk prediction model is linked to the two questions whether the observed outcome is confirmed by the prediction and whether the risk prediction is accurate in predicting the future outcome, respectively. The first phrasing of the question is linked to considering sensitivity and specificity and the latter to the positive and negative predictive values. We present the measures of standardized total gain in positive and negative predictive values dealing with the performance or accuracy of the prediction model for a binary outcome. Both measures provide a useful tool for assessing the performance or accuracy of a set of predictor variables for the prediction of a binary outcome. This concept is a tool for evaluating the optimal prediction model in future research.

Ancillary