Ignorability for general longitudinal data

• 成果类型: Article
• 署名作者: Farewell, D. M.; Huang, C.; Didelez, V.
• 署名单位: Cardiff University; Cardiff University; Leibniz Association; Leibniz Institute for Prevention Research & Epidemiology (BIPS)
• 刊物名称: BIOMETRIKA
• ISSN/ISSBN: 0006-3444
• DOI: 10.1093/biomet/asx020
• 发表日期: 2017
• 页码: 317326
• 关键词: drop-out; inference; models

摘要

Likelihood factors that can be disregarded for inference are termed ignorable. We demonstrate that close ties exist between ignorability and identification of causal effects by covariate adjustment. A graphical condition, stability, plays a role analogous to that of missingness at random, but is applicable to general longitudinal data. Our formulation of ignorability does not depend on any notion of missing data, so is appealing in situations where missing data may not actually exist. Several examples illustrate how stability may be assessed.