Sensitivity Analysis for Nonrandom Dropout: A Local Influence Approach

DOI Web Site Web Site 被引用文献3件

抄録

<jats:p><jats:bold>Summary. </jats:bold> Diggle and Kenward (1994, <jats:italic>Applied Statistics</jats:italic><jats:bold>43</jats:bold>, 49–93) proposed a selection model for continuous longitudinal data subject to nonrandom dropout. It has provoked a large debate about the role for such models. The original enthusiasm was followed by skepticism about the strong but untestable assumptions on which this type of model invariably rests. Since then, the view has emerged that these models should ideally be made part of a sensitivity analysis. This paper presents a formal and flexible approach to such a sensitivity assessment based on local influence (Cook, 1986, <jats:italic>Journal of the Royal Statistical Society, Series B</jats:italic><jats:bold>48</jats:bold>, 133–169). The influence of perturbing a missing‐at‐random dropout model in the direction of nonrandom dropout is explored. The method is applied to data from a randomized experiment on the inhibition of testosterone production in rats.</jats:p>

収録刊行物

  • Biometrics

    Biometrics 57 (1), 7-14, 2001-03

    Oxford University Press (OUP)

被引用文献 (3)*注記

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ