A FLEXIBLE SENSITIVITY ANALYSIS APPROACH FOR UNMEASURED CONFOUNDING WITH MULTIPLE TREATMENTS AND A BINARY OUTCOME WITH APPLICATION TO SEER-MEDICARE LUNG CANCER DATA

• Published in: The annals of applied statistics Vol. 16; no. 2; p. 1014
• Main Authors: Hu, Liangyuan, Zou, Jungang, Gu, Chenyang, Ji, Jiayi, Lopez, Michael, Kale, Minal
• Format: Journal Article
• Language: English
• Published: United States 01.06.2022
• Subjects: Causal inference; ignorability assumption; Bayesian inference; nested multiple imputation; observational data

In the absence of a randomized experiment, a key assumption for drawing causal inference about treatment effects is the ignorable treatment assignment. Violations of the ignorability assumption may lead to biased treatment effect estimates. Sensitivity analysis helps gauge how causal conclusions wil...