Sensitivity Analyses for Means or Proportions with Missing Outcome Data : Epidemiology

Secondary Logo

Journal Logo

Advanced Search
Methods

Sensitivity Analyses for Means or Proportions with Missing Outcome Data

Cole, Stephen R.a; Zivich, Paul N.a; Edwards, Jessie K.a; Shook-Sa, Bonnie E.b; Hudgens, Michael G.b

Author Information

From the aDepartment of Epidemiology, UNC Gillings School of Global Public Health, Chapel Hill, NC

bDepartment of Biostatistics, UNC Gillings School of Global Public Health, Chapel Hill, NC.

Submitted December 5, 2022; accepted May 4, 2023

This study is funded by NIH grants R01AI157758, U01HL146194, and P30AI50410.

Data and code are provided on GitHub (https://github.com/pzivich/publications-code).

Disclosure: The authors report no conflicts of interest.

Correspondence: Stephen Cole, Department of Epidemiology, UNC Gillings School of Global Public Health, UNC Campus Box 7435, Chapel Hill, NC 27599-7435. E-mail: [email protected].

Epidemiology 34(5):p 645-651, September 2023. | DOI: 10.1097/EDE.0000000000001627

Abstract

We describe an approach to sensitivity analysis introduced by Robins et al (1999), for the setting where the outcome is missing for some observations. This flexible approach focuses on the relationship between the outcomes and missingness, where data can be missing completely at random, missing at random given observed data, or missing not at random. We provide examples from HIV that include the sensitivity of the estimation of a mean and proportion under different missingness mechanisms. The approach illustrated provides a method for examining how the results of epidemiologic studies might shift as a function of bias due to missing data.

Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.

Full Text Access for Subscribers:

Not a Subscriber?

Buy
Request Permissions

You can read the full text of this article if you:

Access through Ovid