Hi all,
Our last meeting of the semester will be at 12pm (EST) Wednesday, April 28,
where Isabel Fulcher <https://www.isabelfulcher.com/> (Harvard University)
presents "Using routinely collected data to quantify the burden of
COVID-19: proceed, but with caution."
*Abstract*
Valid estimates for the number of SARS-CoV-2 infections is imperative for
assessing the impact of the COVID-19 pandemic within specific populations.
Here, we discuss ongoing efforts aimed at understanding the state of the
pandemic in two different contexts. First, we focus on seven low- and
middle-income countries where COVID-19 testing has been limited. We propose
using aggregated health systems data to perform syndromic surveillance and
detect potential outbreaks. Second, we focus locally on the City of
Holyoke, Massachusetts where testing is readily available, but racial and
ethnic disparities in testing may obscure the toll of COVID-19 in
historically marginalized communities. Specifically, progress is limited
by: (1) missing information on race and ethnicity in the testing data and
(2) selection bias resulting from access to testing. We provide a
discussion on statistical approaches that can account for these
complexities.
*Zoom link*:
https://harvard.zoom.us/j/97787602526?pwd=Uzh3bVVVS0F4TEVYQTJlV3BQNjcydz09
*Schedule of the workshop*:
https://projects.iq.harvard.edu/applied.stats.workshop-gov3009
Looking forward to seeing you all on Wednesday!
Best,
Soichiro
--
Soichiro Yamauchi
PhD candidate
Harvard University
URL: https://soichiroy.github.io/
Hi all,
Our next virtual meeting will be at 12pm (EST) Wednesday, April 21,
where Kristen
Hunter <https://scholar.harvard.edu/khunter/home>(Harvard) will present
"Conceptualizing experimental controls using the potential outcomes
framework."
*Abstract*
The goal of a well-controlled study is to remove unwanted variation when
estimating the causal effect of the intervention of interest. Experiments
conducted in the basic sciences frequently achieve this goal using
experimental controls, such as "negative'' and "positive'' controls, which
are measurements designed to detect systematic sources of unwanted
variation. Here, we introduce clear, mathematically precise definitions of
experimental controls using potential outcomes. Our definitions provide a
unifying statistical framework for fundamental concepts of experimental
design from the biological and other basic sciences. We discuss
experimental controls as tools for researchers to wield in designing
experiments and detecting potential design flaws, including using controls
to diagnose unintended factors that influence the outcome of interest,
assess measurement error, and identify important subpopulations.
*Zoom link*:
https://harvard.zoom.us/j/97787602526?pwd=Uzh3bVVVS0F4TEVYQTJlV3BQNjcydz09
*Schedule of the workshop*:
https://projects.iq.harvard.edu/applied.stats.workshop-gov3009
Looking forward to seeing you all on Wednesday!
Best,
Soichiro
--
Soichiro Yamauchi
PhD candidate
Harvard University
URL: https://soichiroy.github.io/
Hi all,
Our next virtual meeting will be at 12pm (EST) Wednesday, April 14, where Laura
Forastiere <https://publichealth.yale.edu/profile/laura_forastiere/> (Yale
University) presents "Heterogeneous Treatment and Spillover Effects under
Clustered Network Interference"
*Abstract*:
The bulk of causal inference studies rules out the presence of interference
between units. However, in many real-world scenarios units are
interconnected by social, physical or virtual ties and the effect of a
treatment can spill from one unit to other connected individuals in the
network. In these settings, interference should be taken into account to
avoid biased estimates of the treatment effect, but it can also be
leveraged to save resources and provide the intervention to a lower
percentage of the population where the treatment is more effective and
where the effect can spill over to other susceptible individuals. In fact,
different people might respond differently not only to the treatment
received but also to the treatment received by their network contacts.
Understanding the heterogeneity of treatment and spillover effects can help
policy-makers in the scale-up phase of the intervention, it can guide the
design of targeting strategies with the ultimate goal of making the
interventions more cost-effective, and it might even allow generalizing the
level of treatment spillover effects in other populations. In this paper,
we develop a machine learning method that makes use of tree-based
algorithms and a Horvitz-Thompson estimator to assess the heterogeneity of
treatment and spillover effects with respect to individual, neighborhood
and network characteristics in the context of clustered network
interference. We illustrate how the proposed binary tree methodology
performs in a Monte Carlo simulation study. Additionally, we provide an
application on a randomized experiment aimed at assessing the heterogeneous
effects of information sessions on the uptake of a new weather insurance
policy in rural China.
*Zoom link*:
https://harvard.zoom.us/j/97787602526?pwd=Uzh3bVVVS0F4TEVYQTJlV3BQNjcydz09
*Schedule of the workshop*:
https://projects.iq.harvard.edu/applied.stats.workshop-gov3009
Looking forward to seeing you all on Wednesday!
Best,
Soichiro
--
Soichiro Yamauchi
PhD candidate
Harvard University
URL: https://soichiroy.github.io/
Hi all,
Our next virtual meeting will be at 12pm (EST) Wednesday, April 7
(tomorrow), where David Ham (Harvard) will present "Using Machine Learning
to Test Hypothesis in Conjoint Analysis." This is joint work with Lucas
Janson and Kosuke Imai.
*Abstract*:
Conjoint analysis is a popular experimental design used to measure
multidimensional preferences. Researchers examine how varying a factor of
interest, while controlling for other relevant factors, impacts
decision-making. Currently, there exist two methodological approaches to
analyzing data from a conjoint experiment. The first focuses on estimating
marginal effects of each factor while averaging over the other factors.
Although this allows for straightforward nonparametric estimation using a
design-based approach, the results critically depend on the distribution of
other factors and how interaction effects are aggregated. An alternative
approach is model-based and in principle can compute any quantities of
interest. The primary drawback is that researchers must correctly specify
the model, a challenging task for conjoint analysis with many factors. In
addition, a commonly used logistic regression has poor statistical
properties even with a moderate number of factors. We propose a new
hypothesis testing approach based on the conditional randomization test.
We answer the most fundamental question of conjoint analysis: Does a factor
of interest matter in any way given the other factors? Our methodology is
solely based on the randomization of factors, and hence is free from
assumptions. Yet, it allows researchers to use any test statistic,
including those based on complex machine learning models. As a result, we
are able to combine the strengths of the existing design-based and
model-based approaches. We illustrate the proposed methodology through
conjoint analysis of immigration preferences. An open-source software
package is available for implementing the proposed methodology.
*Zoom link*:
https://harvard.zoom.us/j/97787602526?pwd=Uzh3bVVVS0F4TEVYQTJlV3BQNjcydz09
*Schedule of the workshop*:
https://projects.iq.harvard.edu/applied.stats.workshop-gov3009
Looking forward to seeing you all tomorrow!
Best,
Soichiro
--
Soichiro Yamauchi
PhD candidate
Harvard University
URL: https://soichiroy.github.io/