Hi everyone,
This year's Midwest Political Science Association panels on political
methodology (and everything else) were cancelled due to COVID-19
containment efforts. But on behalf of 2020 MPSA Methods Chair Yiqing Xu
and the IMC advisory board (Michelle Dion, Cassy Dorff, Jeff Harden, Dustin
Tingley, and Chris Zorn), I am pleased to announce that the IMC will host a
special series of summer methodology talks from presenters originally
scheduled to share their work at MPSA!
The International Methods Colloquium (IMC) is a weekly seminar series of
methodology-related talks and roundtable discussions focusing on political
methodology; the series is supported by Wake Forest University and was
previously supported by Rice University and a grant from the National
Science Foundation. The IMC is free to attend from anywhere around the
world using a PC or Mac, a broadband internet connection, and our free
software. You can find out more about the IMC at our website,
http://www.methods-colloquium.com/, where you can join a talk in progress
using the "Watch Now!" link. You can also watch archived talks from
previous IMC seasons at this site. Registration in advance for a talk is
encouraged, but not required.
Note that all talks begin at 12:00 Eastern Time and last precisely one
hour. For this special series of IMC talks, we are presenting two talks
(20-25 minutes each) during a single session, with the remainder of the
time reserved for audience Q&A and discussion among the panelists.
Here is our schedule of presenters (and a link to our Google Calendar):
*May 22* [click here to register
<https://zoom.us/webinar/register/WN_-j7aWpyyRgaosU6iVDhS7Q>]
1. Matt Tyler (Stanford): Rigorous Subjectivity: Demystifying and
Improving Human Coding with Statistical Models
2. Arthur Yu and Robert Gulotty (Chicago): Beyond LATE: Identification
of ATEs of Always-Takers and Never-Takers
*May 29* [click here to register
<https://zoom.us/webinar/register/WN_lL1q4kFDSk6YQJPTrYHaPQ>]
1. Shusei Eshima (Harvard), Kosuke Imai (Harvard), Tomoya Sasaki (MIT):
Keyword Assisted Topic Models
2. JB Duck-Mayr, Roman Garnett, Jacob Montgomery (WUSTL): GPIRT: A
Gaussian Process Model for Item Response Theory
*June 5 * [click here to register
<https://zoom.us/webinar/register/WN_YMboxLn4SQuVGF_83loG_w>]
1. Patrick Wu and Walter Mebane (Michigan): Joint image-text
classification of tweets using BERT and CNN
2. Jason Anastasopoulos (U Georgia): Principled estimation of regression
discontinuity designs with covariates: a machine learning approach
*June 12 * [click here to register
<https://zoom.us/webinar/register/WN_FtD-rQ2ESb6hlyQ-MI60jA>]
1. Bryce Dietrich (U Iowa), Nick Beauchamp (Northeastern), Jielu Yao (U
Iowa), and Yuehong Tai (U Iowa): Has President Trump Changed the Way
Americans Talk About Immigration On Twitter?
2. Naijia Liu (Princeton): A Latent Utility Approach to Missing not at
Random
*June 26* [click here to register
<https://zoom.us/webinar/register/WN_AOQw2rbESp2PY1nzqg17GQ>]
1. Soren Jordan (Auburn) and Andrew Philips (U Colorado Boulder): How to
Cautiously Uncover the 'Black Box' of Tree-Based Machine Learning Models
2. Jared Edgerton (OSU) and Grant Buckles (Gallup): Forecasting rare
events: Predicting terrorist attacks at a subnational level
*July 3 * [click here to register
<https://zoom.us/webinar/register/WN_HUSm2GcZTaC43C06swlHOw>]
1. Haohan Chan and Brian Guay (Duke): Tweets and Completes: Measuring
Individual-level Political Attitudes Using Survey-Matched Tweets
2. Albert Chiu (UCSD) and Yiqing Xu (Stanford): Bayesian Rule Set: A
Quantitative Alternative to Qualitative Comparative Analysis
Additional information for each talk will be released closer to its date.
For this week's talks, I already have additional information available:
1. Matt Tyler (Stanford): Rigorous Subjectivity: Demystifying and Improving
Human Coding with Statistical Models
Abstract: Researchers are often tasked with applying subjective or
contested labels to objects such as text and images. For example,
researchers might hire coders to label the ideological slant of news
articles. For years now, coding practice in political science has been done
on a mostly ad hoc basis. At best, coders are "validated" by checking
whether intercoder reliability meets an arbitrary threshold. In this paper
I show how coding problems can be couched in a modeling framework that
accounts for coding error and heterogeneous coders. Instead of simply
taking coders at their word or resolving disagreements through majority
voting, coding models give probabilistic predictions of an object's true
label. I also introduce the hierarchical Dirichlet Dawid-Skene (HDDS)
model, which is designed for the increasingly more common crowd-sourced
coding projects. I demonstrate these models on real data sets from recent
political science coding projects.
2. Arthur Yu and Robert Gulotty (Chicago): Beyond LATE: Identification of
ATEs of Always-Takers and Never-Takers
Abstract: In the presence of heterogeneous treatment effects, instrumental
variable (IV) estimation only point identifies the local average treatment
effect (LATE). The LATE is an average treatment effect (ATE) for a
subpopulation whose treatment taking decision can be shifted by the
instrument. This paper provides a set of identification results necessary
to extrapolate the LATE to the ATEs of always-takers and never-takers. We
first show that the ATEs of always-takers and never-takers can be written
as the weighted average of marginal treatment effect (MTE) functions. We
then demonstrate that, under further parametric assumptions on the MTE
function, we can point identify the ATEs of always-takers and never-takers.
Furthermore, we show in the absence of these parametric assumptions, we can
nonetheless construct the bounds of the ATEs of always-takers and
never-takers. We prove that the linear programming method developed by
Mogstad et al. (2018) provides bounds that improve in terms of
interpretability and performance over alternative methods that bound the
support of the outcome variable or require monotonicity or smoothness in
the treatment response. We illustrate the proposed methodology using a
simulation study as well as an application based on Kern and Hainmueller
(2009). We find that exposure to West German television reduces support for
communism among never-takers. These never-takers, who would not watch West
German TV even if they had access, act as-if they anticipate the effect of
watching West German TV and thus opt out of exposure.
Please contact me if you need any more information; I hope to see many of
you there for this week's talks
<https://zoom.us/webinar/register/WN_-j7aWpyyRgaosU6iVDhS7Q>!
-JE
--
Dr. Justin Esarey
Associate Professor of Politics and International Affairs
Wake Forest University
Voice: (678) 383-9629
Fax: (336) 758-6104
E-mail: <[log in to unmask]>[log in to unmask]
Web: www.justinesarey.com
**************************************************************
Political Methodology E-Mail List
Editor: Erin Rossiter <[log in to unmask]>
**************************************************************
Send messages to [log in to unmask]
To join the list, cancel your subscription, or modify
your subscription settings visit:
https://www.cambridge.org/core/membership/spm/mailing-list
**************************************************************
|
