Columbia Political Methodology Colloquium

Format

In Fall 2021, we hold seminars in-person on Fridays from 12:10 - 1:30 pm at 707 International Affairs Building (the Lindsay Rogers Room).
We will follow Columbia's COVID-19 policy, and we ask participants to follow it, too. Following the policy on COVID-19, we cannot serve lunch in seminars.

Mailing list

To stay up-to-date about upcoming presentations, please sign-up for our mailing list. You can add the schedule to your Google calendar here.

Upcoming Seminars


2021-2022: Fall Semester


Speaker: David Blei (Columbia; Statistics and Computer Science)

    • Date: November 19th, 2021

    • Time: 12:10 - 1:30 pm (Eastern time)

    • Location: 707 International Affairs Building (the Lindsay Rogers Room)

    • Zoom Link: https://columbiauniversity.zoom.us/j/97873183872

    • Zoom passcode: pmc

    • Title: The Blessings of Multiple Causes

    • Abstract: Causal inference from observational data is a vital problem, but it comes with strong assumptions. Most methods require that we observe all confounders, variables that affect both the causal variables and the outcome variables. But whether we have observed all confounders is a famously untestable assumption. In this talk, I will describe the deconfounder, a way to do causal inference with alternative assumptions than the classical methods require.

      How does the deconfounder work? While traditional causal methods measure the effect of a single cause on an outcome, many modern scientific studies involve multiple causes, different variables whose effects are simultaneously of interest. The deconfounder uses the correlation among multiple causes as evidence for unmeasured confounders, combining unsupervised machine learning and predictive model checking to perform causal inference.

      In this talk, I will describe the deconfounder methodology and discuss the theoretical requirements for the deconfounder to provide unbiased causal estimates. I will touch on some of the academic debates surrounding the deconfounder, and demonstrate the deconfounder on
      real-world data and simulation studies.

      This is joint work with Yixin Wang.

    • Paper Link: https://www.tandfonline.com/doi/full/10.1080/01621459.2019.1686987