Sophie E. Hill

PhD student in Political Science

Harvard University

Biography

I’m a PhD student in political science. I study the politics of economic policy-making. I also dabble in data journalism (see: My Little Crony).

Download my CV

Interests

Public Opinion
Political Economy
Quantitative methods

Education

PhD in Government, (in progress)
Harvard University
MA in Political Science, 2016
Columbia University
MMathPhil in Mathematics & Philosophy, 2013
Oxford University, Balliol College

Research

Matthew Blackwell, Jacob R. Brown, Sophie Hill, Kosuke Imai, and Teppei Yamamoto. “Priming bias versus post-treatment bias in experimental designs.” PDF

More info

Conditioning on variables affected by treatment can induce post-treatment bias when estimating causal effects. Although this suggests that researchers should measure potential moderators before administering the treatment in an experiment, doing so may also bias causal effect estimation if the covariate measurement primes respondents to react differently to the treatment. This paper formally analyzes this trade-off between post-treatment and priming biases in three experimental designs that vary when moderators are measured: pre-treatment, post-treatment, or a randomized choice between the two. We derive nonparametric bounds for interactions between the treatment and the moderator in each design and show how to use substantive assumptions to narrow these bounds. These bounds allow researchers to assess the sensitivity of their empirical findings to either source of bias. We extend the basic framework in two ways. First, we apply the framework to the case of post-treatment attention checks and bound how much inattentive respondents can attenuate estimated treatment effects. Second, we develop a parametric Bayesian approach to incorporate pre-treatment covariates in the analysis to sharpen our inferences and quantify estimation uncertainty. We apply these methods to a survey experiment on electoral messaging. We conclude with practical recommendations for scholars designing experiments.

Teaching

I have taught a range of substantive and methods courses for undergrads, public policy master’s students, and PhD students. I particularly enjoy helping people overcome their fear of statistics using interactive tools!

I was awarded a Certificate of Distinction in Teaching by the Bok Center in 2021, and the Harvard Kennedy School Dean’s Award for Excellence in Teaching in 2022.

Gov 1360 American Public Opinion (undergraduate course), taught by Prof. Stephen Ansolabehere Syllabus

Gov 2006 Formal Political Theory II (graduate course), taught by Prof. James Snyder Syllabus Section slides

HKS API-201 Quantitative Analysis and Empirical Methods (graduate course), taught by Prof.s Teddy Svoronos, Dan Levy et al. Syllabus Section slides

Gov 1780 International Political Economy (undergraduate course), taught by Prof. Jeffry Frieden Syllabus Section slides

HKS API-202 Quantitative Analysis and Empirical Methods (graduate course), taught by Prof.s Benjamin Schneer et al. Syllabus Section slides

Writing & Media

Chumocracy: UK Prime Ministers, Cronyism, and the Pandemic

28 April 2021 • Covid-19 and Democracy Podcast

I spoke with Dr. Peter Finn about why I created “My Little Crony”, and what it says about the state of British political institutions. This episode is part of a series that explores the intersection between the Covid-19 pandemic and democratic politics and policy.

The Tories' ‘chumocracy’ over Covid contracts is destroying public trust

21 November 2020 • The Guardian

Under the cover of an emergency, the government awarded £18bn in coronavirus-related contracts during the first six months of the pandemic, most with no competitive tendering processes.

Will the Knowledge Economy Survive the Pandemic?

19 November 2020 • Political Insight

While many highly-skilled white collar workers have been relatively insulated from the economic impact of the pandemic, the sudden transition to remote working has challenged fundamental assumptions about the knowledge economy.

What I Learnt About the Great Procurement Scandal: Building ‘My Little Crony’

13 November 2020 • Byline Times

“My hope is that tools like mine can help citizens to make sense of complex and fast-unfolding stories and – above all – that greater transparency will fuel action, not apathy.”

Parties have failed voters — but they are still our best hope

12 December 2019 • UK in a Changing Europe

“To borrow Schattschneider’s famous phrase: moving beyond the Brexit gridlock is unthinkable save in terms of parties. But with political trust falling and alienation growing, the question remains: will the parties rise to this challenge before it is too late?”

Projects

Side-projects I do for ~~procrastination~~ fun

Recent & Upcoming Talks

Dataviz in R

A 15 minute talk on dataviz in R, using My Little Crony as an example.

May 4, 2021 3:00 PM — 5:00 PM Zoom

Data

ESS-Partyfacts crosswalk: Crosswalk between ESS codes for political parties to Partyfacts ID. Allows you to merge in information from various party-level datasets (Manifesto Project, ParlGov, etc.)

ESS cumulative dataset: R script to build a cumulative dataset from ESS rounds 1-9, with harmonized variables for vote intention, education, and social class. Also provides an example of using the Partyfacts ID to merge in information from an external dataset: in this case, I use the Manifesto Project data to add a variable for the party family.