A joint project of the Graduate School, Peabody College, and the Jean & Alexander Heard Library

Title page for ETD etd-03232018-135113


Type of Document Dissertation
Author D'Agostino McGowan, Lucy
URN etd-03232018-135113
Title Improving Modern Techniques of Causal Inference: Finite Sample Performance of ATM and ATO Doubly Robust Estimators, Variance Estimation for ATO Estimators, and Contextualized Tipping Point Sensitivity Analyses for Unmeasured Confounding
Degree PhD
Department Biostatistics
Advisory Committee
Advisor Name Title
Frank Harrell, Jr. Committee Chair
Peter Rebeiro Committee Member
Qingxia (Cindy) Chen Committee Member
Robert Alan Greevy, Jr. Committee Member
Keywords
  • propensity score weighting
  • double robust
  • causal inference
  • unmeasured confounding
  • sensitivity analysis
Date of Defense 2018-03-12
Availability unrestricted
Abstract
While estimators that incorporate both direct covariate adjustment and inverse probability weighting have drawn considerable interest, their finite sample properties have been challenged in seminal papers, such as Freedman and Berk (2008). We derive a doubly robust ATO estimator and demonstrate excellent finite sample performance for ATO and ATM doubly robust estimators in the setting of Freedman and Berk (2008). The methods and performance of variance estimators for IPW and IPW doubly robust estimators incorporating the recently defined ATO weights are an important open question in the field. We derive the large-sample variance estimator for the ATO doubly robust estimator for generalized linear models with identity, log, or logistic links. We conduct simulations to compare this estimator to common model-fitting practices, demonstrating under which conditions our estimated variance is preferred. Unobserved confounding remains a limitation for doubly robust estimators. We have worked to reframe the seminal work of Rosenbaum and Rubin (1983), Lin, Psaty, and Kronmal (1998), and Vanderweele and Ding (2017) to a formulation of a sensitivity to unmeasured confounders analysis that appeals to medical researchers. We offer guidelines to researchers for anchoring the tipping point analysis in the context of the study and introduce the R package tipr.
Files
  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  dagostino-mcgowan.pdf 750.27 Kb 00:03:28 00:01:47 00:01:33 00:00:46 00:00:04

Browse All Available ETDs by ( Author | Department )

If you have more questions or technical problems, please Contact LITS.