Data Missing Not at Random in Mobile Health Research: Assessment of the Problem and a Case for Sensitivity Analyses.

Simon B Goldberg Daniel M Bolt Richard J Davidson

Published in: Journal of medical Internet research (2021)

MNAR data because of differential attrition are likely in mHealth RCTs using passive controls. Sensitivity analyses are recommended to allow researchers to assess the potential impact of MNAR on trial results.

Keyphrases

electronic health record
big data
clinical trial
study protocol
phase iii
randomized controlled trial
phase ii
human health
deep learning