Hazards models for human population biology

Authors

  • James W. Wood,

    1. Department of Anthropology, Pennsylvania State University, University Park, Pennsylvania 16802
    2. Population Research Insititute, Pennsylvania State University, University Park, Pennsylvania 16802
    3. Graduate Program in Genetics, Pennsylvania State University, University Park, Pennsylvania 16802
    Search for more papers by this author
  • Darryl J. Holman,

    1. Department of Anthropology, Pennsylvania State University, University Park, Pennsylvania 16802
    2. Population Research Insititute, Pennsylvania State University, University Park, Pennsylvania 16802
    Search for more papers by this author
  • Kenneth M. Weiss,

    1. Department of Anthropology, Pennsylvania State University, University Park, Pennsylvania 16802
    2. Population Research Insititute, Pennsylvania State University, University Park, Pennsylvania 16802
    3. Graduate Program in Genetics, Pennsylvania State University, University Park, Pennsylvania 16802
    Search for more papers by this author
  • Anne V. Buchanan,

    1. Department of Anthropology, Pennsylvania State University, University Park, Pennsylvania 16802
    2. Population Research Insititute, Pennsylvania State University, University Park, Pennsylvania 16802
    Search for more papers by this author
  • Belinda LeFor

    1. Department of Anthropology, Pennsylvania State University, University Park, Pennsylvania 16802
    Search for more papers by this author

Abstract

Population biologists are often interested in examining the effects of continuous biological variables such as measures of growth, body size, nutritional status, and exposure to environmental risk factors, on discerte vital events such as brith, onset of disease, and death. Traditional statistical analyses are unable to cope with several complexities that arise in the study of such effects, including censoring of observations and explanatory variables that change over time. In addition, most traditional methods provide at best empirical rather than etiologic models of the processes of interest. This paper is a review of statistical techniques drawn from the field of hazards analysis that appear to be particularly appropriate for the study of biodemographic events and processes. A general likelihood framework is presented which permits efficient estimation and testing of a wide range of etiologic hazards models. We also review past attempts to model the biological processes underlying age patterns of fertility and mortality. Finally, we discuss how the hazards framework can be adapted to study the quantitative genetics of vital events. ©1992 Wiley-Liss, Inc.

Ancillary