Dear Applied Statistics Workshop Community,
Our next meeting of the semester will be on March 29 (12:00 EST). James M.
Robins will present "Target Trials and Structural Nested Models: Emulating
RCTs using Observational Longitudinal Data."
<Where>
CGIS K354
Bagged lunches are available for pick-up at 11:40 (CGIS K354).
Zoom:
https://harvard.zoom.us/j/99181972207?pwd=Ykd3ZzVZRnZCSDZqNVpCSURCNnVvQT09
<Abstract>
Target trials are RCTs one would like to conduct but cannot for ethical,
financial, and/or logistical reasons. Consequently, we must emulate such
trials from observational data. A novel aspect of target trial methodology
is that, for purposes of data analysis, each subject in the observational
study is ‘enrolled’ in all target trials for which the subject is eligible,
instead of a single trial. I will describe recent theoretical results
connecting target trial methodology and structural nested models. I will
discuss a novel inferential conundrum that arises from this connection.
Finally I will discuss the question: How do we validate causal estimates
from observational data.
<2022-2023 Schedule>
GOV 3009 Website:
https://projects.iq.harvard.edu/applied.stats.workshop-gov3009
Calendar:
https://calendar.google.com/calendar/embed?src=c_3v93pav9fjkkldrbu9snbhned8…
Best,
Shusei
Dear Applied Statistics Workshop Community,
Our next meeting of the semester will be on March 22 (12:00 EST). Carlos
Velasco Rivera will present "On-Platform Experimental Research on Facebook
and Instagram in the 2020 Election."
<Where>
Hybrid: CGIS K354 or Zoom (the presenter will join us via Zoom)
Bagged lunches are available for pick-up at 11:40 (CGIS K354).
Zoom:
https://harvard.zoom.us/j/99181972207?pwd=Ykd3ZzVZRnZCSDZqNVpCSURCNnVvQT09
<Abstract>
We will discuss a groundbreaking collaboration among over two dozen
independent (that is, not paid by Meta) academics and a team of Meta
researchers. Since early 2020, this group has worked together to evaluate
the role of Facebook and Instagram in the 2020 U.S. presidential election.
The collaboration has, as of now, resulted in over a dozen pre-registered
(observational and experimental) designs for academic research papers. In
this presentation, we will focus on the experimental interventions that
were designed to test the causal impact of Facebook and Instagram on all of
the project’s key variables of inquiry: political participation; political
polarization; knowledge and misperceptions; and beliefs about democratic
norms. The project included multiple experiments, including full
deactivation of platform use as well as various changes to the way in which
participants encountered information on the platform.
<2022-2023 Schedule>
GOV 3009 Website:
https://projects.iq.harvard.edu/applied.stats.workshop-gov3009
Calendar:
https://calendar.google.com/calendar/embed?src=c_3v93pav9fjkkldrbu9snbhned8…
Best,
Shusei
Dear Applied Statistics Workshop Community,
Our next meeting of the semester will be on March 8 (12:00 EST). Cory
McCartan will present "Estimating Racial Disparities when Race is Not
Observed."
<Where>
CGIS K354
Bagged lunches are available for pick-up at 11:40 (CGIS K354).
Zoom:
https://harvard.zoom.us/j/99181972207?pwd=Ykd3ZzVZRnZCSDZqNVpCSURCNnVvQT09
<Abstract>
The estimation of racial disparities in health care, financial services,
voting, and other contexts is often hampered by the lack of
individual-level racial information in administrative records. In many
cases, the law prohibits the collection of such information to prevent
direct racial discrimination. As a result, many analysts have adopted
Bayesian Improved Surname Geocoding (BISG), which combines individual names
and addresses with the Census data to predict race. Although BISG tends to
produce well-calibrated racial predictions, its residuals are often
correlated with the outcomes of interest, yielding biased estimates of
racial disparities. We propose an alternative identification strategy that
corrects this bias. The proposed strategy is applicable whenever one’s
surname is conditionally independent of the outcome given their
(unobserved) race, residence location, and other observed characteristics.
Leveraging this identification strategy, we introduce a new class of
models, Bayesian Instrumental Regression for Disparity Estimation (BIRDiE),
that estimate racial disparities by using surnames as a high-dimensional
instrumental variable for race. Our estimation method is scalable, making
it possible to analyze large-scale administrative data. A validation study
based on the North Carolina voter file shows that BIRDiE reduces error by
up to 84% in comparison to the standard approaches for estimating racial
differences in party identification.
<2022-2023 Schedule>
GOV 3009 Website:
https://projects.iq.harvard.edu/applied.stats.workshop-gov3009
Calendar:
https://calendar.google.com/calendar/embed?src=c_3v93pav9fjkkldrbu9snbhned8…
Best,
Shusei
