Dear workshop community,
We will convene for the Applied Statistics Workshop (Gov 3009) next week on
Wednesday (10/3).
The speaker is* Naoki Egami* (Princeton), who will be presenting his paper
"Causal Diffusion Analysis with Stationarity: How Hate Crimes Diffuse
across Space" (paper link here
<https://scholar.princeton.edu/negami/publications/identification-causal-dif…>).
*Where:* CGIS Knafel Building, Room K354 (see this link
<https://map.harvard.edu/?bld=04471&level=9> for directions).
*When: *Wednesday, October 3rd at 12 noon - 1:30 pm.
*Abstract:* Although social scientists have long been interested in the
process through which ideas and behavior diffuse, the identification of
causal diffusion effects, also known as peer effects, remains challenging.
Many scholars consider the commonly used assumption of no omitted
confounders to be untenable due to contextual confounding and homophily
bias. To address this long-standing identification problem, I introduce a
class of *stationary* causal directed acyclic graphs (DAGs), which
represent the time-invariant nonparametric causal structure. I first show
that this stationary causal DAG implies a new statistical test that can
detect a wide range of biases, including the two types mentioned above. The
proposed test allows researchers to empirically assess the contentious
assumption of no omitted confounders. In addition, I develop a
difference-in-difference style estimator that can directly correct biases
under an additional parametric assumption. Leveraging the proposed methods,
I study the spatial diffusion of hate crimes in Germany. After correcting
large upward bias in existing studies, I find hate crimes diffuse only to
areas that have a high proportion of school dropouts. To highlight the
general applicability of the proposed approach, I also analyze the network
diffusion of human rights norms. The proposed methodology is implemented in
a forthcoming open source software package.
*All are welcome! Lunch is provided! *
Best,
Connor Jerzak
Applied Statistics Workshop -- Graduate Student Coordinator
An anonymous feedback form for the workshop can be found here at this link
<https://docs.google.com/forms/d/e/1FAIpQLScp4lPVBtp4Akf6K6ggmfcTUSIUHEJX89-…>.
Workshop listserv sign-up at this link
<https://lists.fas.harvard.edu/mailman/listinfo/gov3009-l>.
*FINAL REMINDER --- Applied Statistics Workshop TOMORROW (9/26) at 12 noon*
*Lunch provided --- All are welcome *
------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------
Dear workshop community,
We will convene for the Applied Statistics Workshop (Gov 3009) tomorrow on
Wednesday (9/26).
The speaker is* Shihao Yang* (Harvard Statistics), who will be presenting
his paper "Big data, Google, and infectious disease prediction: A
statistical perspective".
*Where:* CGIS Knafel Building, Room K354 (see this link
<https://map.harvard.edu/?bld=04471&level=9> for directions).
*When: *Wednesday, September 26th at 12 noon - 1:30 pm.
*Abstract:* Big data generated from the internet have great potential in
tracking and predicting massive social activities, in particular infectious
diseases, whose accurate real-time prediction could help public health
officials make timely decisions to save lives. We introduce a model ARGO
(AutoRegression with GOogle search data / AutoRegression with General
Online data) that has successfully utilized publicly available Google
search data, with/without cloud-based electronic health records, to
estimate current and near-future influenza-like illness activity level
and/or dengue fever activity level for United States and five other
countries around the globe. Our regularized multivariate regression model
dynamically selects the most appropriate variables for prediction every
week, and significantly outperforms all previous internet-based tracking
models, including Google Flu Trends and Google Dengue Trends. We further
extend the model to multiple geographical resolution, tracking infectious
disease not only at national level but also at regional level, with
spatial-temporal information pooling, making it flexible, self-correcting,
robust and scalable.
*All are welcome! Lunch is provided! *
Best,
Connor Jerzak
Applied Statistics Workshop -- Graduate Student Coordinator
An anonymous feedback form for the workshop can be found here at this link
<https://docs.google.com/forms/d/e/1FAIpQLScp4lPVBtp4Akf6K6ggmfcTUSIUHEJX89-…>.
Dear workshop community,
We will convene for the Applied Statistics Workshop (Gov 3009) next week on
Wednesday (9/26).
The speaker is* Shihao Yang* (Harvard Statistics) who will be presenting
his paper "Big data, Google, and infectious disease prediction: a
statistical perspective".
*Where:* CGIS Knafel Building, Room K354 (see this link
<https://map.harvard.edu/?bld=04471&level=9> for directions).
*When: *Wednesday, September 26th at 12 noon - 1:30 pm.
*Abstract:* Big data generated from the internet have great potential in
tracking and predicting massive social activities, in particular infectious
diseases, whose accurate real-time prediction could help public health
officials make timely decisions to save lives. We introduce a model ARGO
(AutoRegression with GOogle search data / AutoRegression with General
Online data) that has successfully utilized publicly available Google
search data, with/without cloud-based electronic health records, to
estimate current and near-future influenza-like illness activity level
and/or dengue fever activity level for United States and five other
countries around the globe. Our regularized multivariate regression model
dynamically selects the most appropriate variables for prediction every
week, and significantly outperforms all previous internet-based tracking
models, including Google Flu Trends and Google Dengue Trends. We further
extend the model to multiple geographical resolution, tracking infectious
disease not only at national level but also at regional level, with
spatial-temporal information pooling, making it flexible, self-correcting,
robust and scalable.
*All are welcome! Lunch is provided! *
Best,
Connor Jerzak
Applied Statistics Workshop -- Graduate Student Coordinator
An anonymous feedback form for the workshop can be found here at this link
<https://docs.google.com/forms/d/e/1FAIpQLScp4lPVBtp4Akf6K6ggmfcTUSIUHEJX89-…>.
*FINAL REMINDER --- Applied Statistics Workshop TOMORROW (9/19) at 12 noon*
*Lunch provided --- All are welcome *
------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------
Dear workshop community,
We will convene for the Applied Statistics Workshop (Gov 3009) next week on
Wednesday (9/19).
The speaker is* Aaron Kaufman * (Harvard PhD candidate; job market
candidate) who will be presenting his paper "An Automated Method to
Estimate Survey Question Bias" (paper link here
<https://projects.iq.harvard.edu/files/applied.stats.workshop-gov3009/files/…>).
*Where:* CGIS Knafel Building, Room K354 (see this link
<https://map.harvard.edu/?bld=04471&level=9> for directions).
*When: *Wednesday, September 19th at 12 noon - 1:30 pm.
*Abstract: *Many survey researchers are interested in gauging public
support for government policy, but there is strong evidence that a
question’s wording affects responses to it. I develop the first automated
and scalable method to predict the magnitude and direction of the partisan
bias a question’s wording may impose on survey responses, and show using a
series of survey experiments that it outperforms public opinion scholars in
predicting that bias. Using a novel data set of almost one million survey
questions from 1997 to 2017, I then examine trends in partisan survey
question biases over time. I find that while questions related to economic
issues are relatively unbiased, questions related to Barack Obama become
steadily more conservatively biased from 2008 to 2017. Questions related to
abortion and immigration are generally conservative, while questions
related to healthcare and education are consistently liberal.
Substantively, my results suggest that measurements of American public
opinion are systematically biased; I discuss the implications of this
result for democratic representation. Methodologically, this paper opens up
new opportunities for studying ideology from text, and for improving survey
methodology and measurement in public opinion.
*All are welcome! Lunch is provided! *
Best,
Connor Jerzak
Applied Statistics Workshop -- Graduate Student Coordinator
An anonymous feedback form for the workshop can be found here at this link
<https://docs.google.com/forms/d/e/1FAIpQLScp4lPVBtp4Akf6K6ggmfcTUSIUHEJX89-…>.
Dear workshop community,
We will convene for the Applied Statistics Workshop (Gov 3009) next week on
Wednesday (9/19).
The speaker is* Aaron Kaufman * (Harvard PhD candidate; job market
candidate) who will be presenting his paper "An Automated Method to
Estimate Survey Question Bias" (paper link here
<https://projects.iq.harvard.edu/files/applied.stats.workshop-gov3009/files/…>).
*Where:* CGIS Knafel Building, Room K354 (see this link
<https://map.harvard.edu/?bld=04471&level=9> for directions).
*When: *Wednesday, September 19th at 12 noon - 1:30 pm.
*Abstract: *Many survey researchers are interested in gauging public
support for government policy, but there is strong evidence that a
question’s wording affects responses to it. I develop the first automated
and scalable method to predict the magnitude and direction of the partisan
bias a question’s wording may impose on survey responses, and show using a
series of survey experiments that it outperforms public opinion scholars in
predicting that bias. Using a novel data set of almost one million survey
questions from 1997 to 2017, I then examine trends in partisan survey
question biases over time. I find that while questions related to economic
issues are relatively unbiased, questions related to Barack Obama become
steadily more conservatively biased from 2008 to 2017. Questions related to
abortion and immigration are generally conservative, while questions
related to healthcare and education are consistently liberal.
Substantively, my results suggest that measurements of American public
opinion are systematically biased; I discuss the implications of this
result for democratic representation. Methodologically, this paper opens up
new opportunities for studying ideology from text, and for improving survey
methodology and measurement in public opinion.
*All are welcome! Lunch is provided! *
Best,
Connor Jerzak
Applied Statistics Workshop -- Graduate Student Coordinator
An anonymous feedback form for the workshop can be found here at this link
<https://docs.google.com/forms/d/e/1FAIpQLScp4lPVBtp4Akf6K6ggmfcTUSIUHEJX89-…>.
*FINAL REMINDER --- Applied Statistics Workshop TOMORROW (9/12) at 12 noon*
*Lunch provided --- All are welcome *
------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------
Dear workshop community,
We will convene for the Applied Statistics Workshop (Gov 3009) tomorrow,
Wednesday (9/12).
The speaker is* Junming Huang * (Princeton postdoc) who will be presenting
his paper "Quantifying Gender Inequality in Scientific Careers" (no paper
link).
*Where:* CGIS Knafel Building, Room K354 (see this link
<https://map.harvard.edu/?bld=04471&level=9> for directions).
*When: *Wednesday, September 12th at 12 noon - 1:30 pm.
*Abstract: *Gender inequality in academic careers, documented across all
disciplines and countries, extends beyond the fraction of women involved in
research: compared to their male colleagues, women publish less over the
course of their careers and their work acquires fewer citations. Yet, all
existing evidence is limited to selected countries or disciplines,
restricting our ability assess the roots and implications of the gender
disparity. Here we analyzed a large corpus of scientific publications since
1900, identifying the gender and reconstructing the full publishing career
of over 1.5 million authors from most scientific disciplines and countries,
allowing us to quantify the processes and outcomes for women and men in
science. We confirm that men have higher total productivity and total
impact than women, a pattern impacting all disciplines and most countries.
Surprisingly, we find no systematic difference between the annual
productivity of male and female scientists, not only offering a
gender-invariant productivity measure, but also suggesting that the
observed gender gaps are rooted in gender dependent dropout rates. We find
that not only do women leave academia at a higher rate than men, but
surprisingly, this gap in dropout rate is greater for the more productive
women. We show that when we control for these two gender-specific dropout
rates, the career gender gaps in both productivity and impact vanish.
Identifying the driving forces of gender gaps can help rephrase the
conversation about gender inequality around the sustainability of women’s
careers in academia, with important consequences for policy makers and
academic institutions.
*All are welcome! Lunch is provided! *
Best,
Connor Jerzak
Applied Statistics Workshop -- Graduate Student Coordinator
An anonymous feedback form for the workshop can be found here at this link
<https://docs.google.com/forms/d/e/1FAIpQLScp4lPVBtp4Akf6K6ggmfcTUSIUHEJX89-…>.
Dear workshop community,
We will convene for the Applied Statistics Workshop (Gov 3009) next week on
Wednesday (9/12).
The speaker is* Junming Huang * (Princeton postdoc) who will be presenting
his paper "Quantifying Gender Inequality in Scientific Careers" (no paper
link).
*Where:* CGIS Knafel Building, Room K354 (see this link
<https://map.harvard.edu/?bld=04471&level=9> for directions).
*When: *Wednesday, September 12th at 12 noon - 1:30 pm.
*Abstract: *Gender inequality in academic careers, documented across all
disciplines and countries, extends beyond the fraction of women involved in
research: compared to their male colleagues, women publish less over the
course of their careers and their work acquires fewer citations. Yet, all
existing evidence is limited to selected countries or disciplines,
restricting our ability assess the roots and implications of the gender
disparity. Here we analyzed a large corpus of scientific publications since
1900, identifying the gender and reconstructing the full publishing career
of over 1.5 million authors from most scientific disciplines and countries,
allowing us to quantify the processes and outcomes for women and men in
science. We confirm that men have higher total productivity and total
impact than women, a pattern impacting all disciplines and most countries.
Surprisingly, we find no systematic difference between the annual
productivity of male and female scientists, not only offering a
gender-invariant productivity measure, but also suggesting that the
observed gender gaps are rooted in gender dependent dropout rates. We find
that not only do women leave academia at a higher rate than men, but
surprisingly, this gap in dropout rate is greater for the more productive
women. We show that when we control for these two gender-specific dropout
rates, the career gender gaps in both productivity and impact vanish.
Identifying the driving forces of gender gaps can help rephrase the
conversation about gender inequality around the sustainability of women’s
careers in academia, with important consequences for policy makers and
academic institutions.
*All are welcome! Lunch is provided! *
Best,
Connor Jerzak
Applied Statistics Workshop -- Graduate Student Coordinator
An anonymous feedback form for the workshop can be found here at this link
<https://docs.google.com/forms/d/e/1FAIpQLScp4lPVBtp4Akf6K6ggmfcTUSIUHEJX89-…>.
Dear workshop community,
We will convene the first Applied Statistics Workshop (Gov 3009) this week
on Wednesday (9/5).
The speaker is* Alberto Abadie* (MIT Economics faculty) who will be
presenting his paper "Statistical Non-Significance in Empirical
Economics" (paper
link here <https://economics.mit.edu/files/14851>).
*Where:* CGIS Knafel Building, Room K354 (see this link
<https://map.harvard.edu/?bld=04471&level=9> for directions).
*When: *Wednesday, September 5th at 12 noon - 1:30 pm.
*Abstract: *Statistical significance is often interpreted as providing
greater information than non-significance. In this article we show,
however, that rejection of a point null often carries very little
information, while failure to reject may be highly informative. This is
particularly true in empirical contexts that are typical and even prevalent
in economics, where data sets are large and there are rarely reasons to put
substantial prior probability on a point null. Our results challenge the
usual practice of conferring point null rejections a higher level of
scientific significance than non-rejections. Therefore, we advocate a
visible reporting and discussion of non-significant results.
*All are welcome! Lunch is provided! *
Best,
Connor Jerzak
Applied Statistics Workshop -- Graduate Student Coordinator