Targeted maximum likelihood estimation of causal effects with interference: a simulation study

Details

• Alternative Title:
  Stat Med
• Personal Author:
  Zivich, Paul N ; Hudgens, Michael G ; Brookhart, M Alan ; Moody, James ; Weber, David J ; Aiello, Allison E
• Description:
  Interference, the dependency of an individual's potential outcome on the exposure of other individuals, is a common occurrence in medicine and public health. Recently, targeted maximum likelihood estimation (TMLE) has been extended to settings of interference, including in the context of estimation of the mean of an outcome under a specified distribution of exposure, referred to as a policy. This paper summarizes how TMLE for independent data is extended to general interference (network-TMLE). An extensive simulation study is presented of network-TMLE, consisting of four data generating mechanisms (unit-treatment effect only, spillover effects only, unit-treatment and spillover effects, infection transmission) in networks of varying structures. Simulations show that network-TMLE performs well across scenarios with interference, but issues manifest when policies are not well-supported by the observed data, potentially leading to poor confidence interval coverage. Guidance for practical application, freely available software, and areas of future work are provided.
• Subjects:
  Causality Computer Simulation Humans Likelihood Functions
• Keywords:
  Interference Networks Peer Effects Spillover Effects Targeted Maximum Likelihood Estimation
• Source:
  Stat Med. 41(23):4554-4577
• Pubmed ID:
  35852017
• Pubmed Central ID:
  PMC9489667
• Document Type:
  Journal Article
• Funding:
  T32 AI007001/AI/NIAID NIH HHSUnited States/ ; R01 AI085073/AI/NIAID NIH HHSUnited States/ ; R01-EB025021/EB/NIBIB NIH HHSUnited States/ ; U01-CK000185/CC/CDC HHSUnited States/ ; P2C-HD050924/HD/NICHD NIH HHSUnited States/ ; R01-AI085073/NH/NIH HHSUnited States/ ; U01 CK000185/CK/NCEZID CDC HHSUnited States/ ; T32 HD091058/HD/NICHD NIH HHSUnited States/ ; U01 AI103390/AI/NIAID NIH HHSUnited States/ ; P2C HD050924/HD/NICHD NIH HHSUnited States/ ; U01 HL146194/HL/NHLBI NIH HHSUnited States/ ; T32-HD091058/HD/NICHD NIH HHSUnited States/ ; R01 EB025021/EB/NIBIB NIH HHSUnited States/
• Volume:
  41
• Issue:
  23
• Collection(s):
  CDC Public Access
• Main Document Checksum:
  urn:sha-512:0ee518fceb040a108f059c1439fefaa63d74acbaa60b911fd0dddfea4a7354e35cfb1196b4c689fceb679cdad93873b7a088f3d6f06cfbc554921efa782667a5
• Download URL:
  https://stacks.cdc.gov/view/cdc/121532/cdc_121532_DS1.pdf
• File Type:
  [PDF - 4.23 MB ]