Bayesian Inference for Sequential Treatments Under Latent Sequential Ignorability. Issue 531 (2nd July 2020)

• Record Type: Journal Article
• Authors: Ricciardi, Federico; Mattei, Alessandra; Mealli, Fabrizia
• Is Part Of: Journal of the American Statistical Association. Volume 115:Issue 531(2020)
• Page Start: 1498
• Page End: 1517
• Publication Date: 2020-07-02
• Subjects: Longitudinal treatments -- Principal stratification -- Rubin causal model -- Sequential ignorablity; Statistics -- Periodicals; Statistics -- Periodicals; Statistiques -- Périodiques; États-Unis -- Statistiques -- Périodiques; 519.5
• DOI: 10.1080/01621459.2019.1623039
• Languages: English
• ISSNs: 0162-1459

Abstract

Abstract: We focus on causal inference for longitudinal treatments, where units are assigned to treatments at multiple time points, aiming to assess the effect of different treatment sequences on an outcome observed at a final point. A common assumption in similar studies is sequential ignorability (SI): treatment assignment at each time point is assumed independent of future potential outcomes given past observed outcomes and covariates. SI is questionable when treatment participation depends on individual choices, and treatment assignment may depend on unobservable quantities associated with future outcomes. We rely on principal stratification to formulate a relaxed version of SI: latent sequential ignorability (LSI) assumes that treatment assignment is conditionally independent on future potential outcomes given past treatments, covariates, and principal stratum membership, a latent variable defined by the joint value of observed and missing intermediate outcomes. We evaluate SI and LSI, using theoretical arguments and simulation studies to investigate the performance of the two assumptions when one holds and inference is conducted under both. Simulations show that when SI does not hold, inference performed under SI leads to misleading conclusions. Conversely, LSI generally leads to correct posterior distributions, irrespective of which assumption holds.