Standard Article

Outcome-Dependent Selection Models

Environmental Health

  1. Jieli Ding1,
  2. Tsui-shan Eva Lu2,
  3. Haibo Zhou3

Published Online: 15 JAN 2013

DOI: 10.1002/9780470057339.vao018.pub2

Encyclopedia of Environmetrics

Encyclopedia of Environmetrics

How to Cite

Ding, J., Eva Lu, T.-s. and Zhou, H. 2013. Outcome-Dependent Selection Models . Encyclopedia of Environmetrics. 4.

Author Information

  1. 1

    Wuhan University, Wuhan, Hubei, China

  2. 2

    National Taiwan Normal University, Taipei, Taiwan

  3. 3

    University of North Carolina at Chapel Hill, North Carolina, USA

Publication History

  1. Published Online: 15 JAN 2013

Abstract

An outcome-dependent selection (ODS) is a retrospective sampling scheme where one observes the environmental exposure/covariates with a probability that depends on the observed outcome values. By allowing the selection probability of each individual to depend on the outcome variable, ODS design can reduce the cost of the study and improve the efficiency. The case-control study and case-cohort study in epidemiology are well-known examples of ODS schemes. We review recent advances in research on ODS designs with a continuous response. This includes inferences on more sophisticated designs with survival data, clustered/longitudinal data, two-stage ODS design, and outcome and auxiliary-dependent (OADS) schemes.

Keywords:

  • outcome-dependent