Section outline

  • Confounding and Interaction I: General Principles

    Definition and manifestations of confounding; use of counterfactual model to conceptualize origins of confounding; confounding vs confounders; use of directed acyclic graphs (DAGs) to demonstrate and identify confounding and other bias; nuisance causal pathways; importance of defining the research question and understanding the biological system to prevent confounding

    Faculty:  Jeffrey Martin

    • Lecture Slides:

    • Confounding I 2021 File

    • Lecture Audio/Video Recording (Access restricted to registered students): 

    • Watch 2021 URL
      Not available unless: You belong to a group in Registered Students Only

    • Large Group Discussion (Access restricted to registered students):
      Brief formal review of lecture followed by question and answer discussion. Recorded lecture should be viewed prior to this session.

    • Watch 2021 (Part 1) Media Resource
      Not available unless: You belong to Registered Students Only
    • Watch 2021 Part 2 Media Resource
      Not available unless: You belong to Registered Students Only

    • Recommended Reading:

    •   S & N: Ch. 5 except section 5.4

    • Notes on reading for Confounding and Interaction I File
    • Digitale et al. Tutorial on directed acyclic graphs. J Clin Epi 2021 File
      Not available unless: Your ID number contains 02
    • Hernan MA et al. Causal knowledge as a prerequisite for confounder evaluation. AJE 156:176-184, 2002. File
      Not available unless: Your ID number contains 02
    • dagitty.net, an open source browser-based environment for creating, editing, and analyzing directed acyclic graphs. URL
    • DAGitty dot net v3.0 instructions File

    • Optional Reading:

    • Greenland Pearl Robins. Causal diagrams for epidemiologic research. Epidemiology 10:37-48,1999. File
      Not available unless: Your ID number contains 02
    • Cole S, Hernan M. Fallibility in estimating direct effects. IJE 31:163-165, 2002. File
      Not available unless: Your ID number contains 02
    • Maldonado G and Greenland S. Estimating causal effects. Int J Epi 31:422-429, 2002. File
      Not available unless: Your ID number contains 02
    • Richiardi L et al. Mediation analysis in epidemiology IJE 42:1511-1519, 2013 File
      Not available unless: Your ID number contains 02
    • Suzuki E et al. Causal Diagrams: Pitfalls and Tips. J of Epi 30:153-162, 2020. File
      Not available unless: Your ID number contains 02

    • Assignment: Problem Set 9

    • Problem Set 9 Confounding and Interaction I 2021 File

    • Assignment Due Date:  November 16, 2021 at the beginning of Small Group Section

    • Assignment Answer Key (Access restricted to registered students):

    • Problem Set 9 Confounding and Interaction I 2021 Answer Key File
    • Problem Set 9 Confounding and Interaction I 2021 Answer Key File