Section outline

  • Lecture:  Multi-level and causal analyses

    Approaches to analyzing complex data to investigate influence across multiple levels and to estimate causal effects.

    Faculty:  Maria Glymour

    Location:      Mission Hall, Conference Room 2700

    • Session Slides:

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

    • Required Reading:

    • Arcaya Multilevel File
      Not available unless: Your ID number contains 02
    • Diez-Roux multilevel File
      Not available unless: Your ID number contains 02
    • Hamad EITC ChildDev File
      Not available unless: Your ID number contains 02
    • Kawachi CausalInf MoneySchoolingHealth File
      Not available unless: Your ID number contains 02

    • Resources:

                 WebEx Login information

                 https://webmeeting.ucsf.edu

                 Meeting Number: 991 016 883

                 Audio Connection: +1 415-514-1000 (Toll)

    • Assignment: Below are discussion questions we will consider in class, that you should be thinking about as you do the reading. If you will not attend class, please submit written responses to each question of approximately one half to one page per question (email to christine.dehlendorf@ucsf.edu).

      1. Why do observational studies where participants have not been randomized to exposures of interest, such as    income or exposure to a policy change, face such great challenges in proving causation?
      2.  What are some ways that researchers get around these challenges in an attempt to make causal claims in observational studies?
      3. How do multi-level models attempt to address the macro-level factors the authors of last week’s articles considered so important?
      4. What research questions in your area of interest do you think could benefit from multi-level analyses? Why?