Get access
Advertisement

Approximate models for aggregate data when individual-level data sets are very large or unavailable

Authors

  • Erol A. Peköz,

    Corresponding author
    1. Boston University School of Management, 595 Commonwealth Avenue, Boston, MA 02215, U.S.A.
    • Boston University School of Management, 595 Commonwealth Avenue, Boston, MA 02215, U.S.A.
    Search for more papers by this author
  • Michael Shwartz,

    1. Boston University School of Management, 595 Commonwealth Avenue, Boston, MA 02215, U.S.A.
    2. Center for Organization, Leadership and Management Research, VA Boston Healthcare System, Boston, MA, U.S.A.
    Search for more papers by this author
  • Cindy L. Christiansen,

    1. Boston University School of Public Health, 715 Albany Street, T-3W, Boston, MA 02118, U.S.A.
    Search for more papers by this author
  • Dan Berlowitz

    1. Center for Health Quality, Outcomes and Economic Research, Bedford VA Hospital, 200 Springs Road, Bedford, MA 01730, U.S.A.
    Search for more papers by this author

Abstract

In this article, we study a Bayesian hierarchical model for profiling health-care facilities using approximately sufficient statistics for aggregate facility-level data when the patient-level data sets are very large or unavailable. Starting with a desired patient-level model, we give several approximate models and the corresponding summary statistics necessary to implement the approximations. The key idea is to use sufficient statistics from an approximate model fitted by matching up derivatives of the models' log-likelihood functions. This derivative matching approach leads to an approximation that performs better than the commonly used approximation given in the literature. The performance of several approximation approaches is compared using data on 5 quality indicators from 32 Veterans Administration nursing homes. Copyright © 2010 John Wiley & Sons, Ltd.

Get access to the full text of this article

Ancillary