Local sensitivity approximations for selectivity bias

  1. John Copas1,
  2. Shinto Eguchi2

Article first published online: 21 APR 2002

DOI: 10.1111/1467-9868.00318

Issue

Journal of the Royal Statistical Society: Series B (Statistical Methodology)

Journal of the Royal Statistical Society: Series B (Statistical Methodology)

Volume 63, Issue 4, pages 871–895, 2001

Additional Information

How to Cite

Copas, J. and Eguchi, S. (2001), Local sensitivity approximations for selectivity bias. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63: 871–895. doi: 10.1111/1467-9868.00318

Author Information

  1. 1

    University of Warwick, Coventry, UK,

  2. 2

    Institute of Statistical Mathematics, Tokyo, Japan

* John Copas Department of Statistics, University of Warwick, Coventry, CV4 7AL, UK. jbc@stats.warwick.ac.uk

Publication History

  1. Issue published online: 21 APR 2002
  2. Article first published online: 21 APR 2002

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (289K)

Keywords:

  • Ignorability;
  • Missing data;
  • Selection bias;
  • Sensitivity analysis

Observational data analysis is often based on tacit assumptions of ignorability or randomness. The paper develops a general approach to local sensitivity analysis for selectivity bias, which aims to study the sensitivity of inference to small departures from such assumptions. If M is a model assuming ignorability, we surround M by a small neighbourhood N defined in the sense of Kullback–Leibler divergence and then compare the inference for models in N with that for M. Interpretable bounds for such differences are developed. Applications to missing data and to observational comparisons are discussed. Local approximations to sensitivity analysis are model robust and can be applied to a wide range of statistical problems.

Get PDF (289K)