Book
Reproducible Research with R and RStudio, 2nd Edition
Chapman and Hall/CRC Press. ISBN 978-1498715379. 2015.
Website with sample chapters.
Source files on GitHub.
Review in The American Statistician:
... advanced undergraduate students in mathematics, statistics, and similar fields as well as students just beginning their graduate studies would benefit the most from reading this book. Many more experienced R users or second-year graduate students might find themselves thinking, ‘I wish I’d read this book at the start of my studies, when I was first learning R!’ … a good text for beginning graduate students or advanced undergraduate students who are just starting to do technical research...
Review by the Mathematical Association of America:
I entered the world of data computing with great reluctance, and only because I saw the benefits of teaching statistics with R, even for elementary students. The first edition of Reproducible Research with R and RStudio was an invaluable companion in the early stages of my journey, and I trust that the second edition will be equally useful to aspiring data analysts.
Peer reviewed journal articles
Explaining Variation and Change in Supervisory Confidentiality in the European Union
with Mark Hallerberg
Accepted at the West European Politics.
The Measurement of Real-Time Perceptions of Financial Stress: Implications for political science
with Mark Hallerberg
Forthcoming at the British Journal of Political Science.
Download earlier working draft PDF.
Financial Regulatory Transparency, International Institutions, and Sovereign Borrowing Costs
with Mark Copelovitch and Mark Hallerberg
Accepted at International Studies Quarterly.
Download PDF.
Download the Financial Data Transparency Index and replication code.
Interpreting Fiscal Accounting Rules in the European Union
with Mark Hallerberg
Journal of European Public Policy.
Download PDF.
Information and Financial Crisis Policymaking
with Mícheál O'Keeffe
Journal of European Public Policy. 2017. 24(3): 386-405.
Download PDF.
Statistical Agencies and Responses to Financial Crises: Eurostat, Bad Banks, and the ESM
West European Politics. 2016. 39(3): 545-564.
with Mark Hallerberg
Download publication PDF.
Two Sword Lengths Apart: Credible commitment problems and physical violence in democratic national legislatures
Journal of Peace Research. 2016. 53(1): 130-145.
Download publication PDF or pre-publication PDF.
Write up on the Monkey Cage with Emily Beaulieu.
Applied to understanding violence in the Ukrainian Parliament in VoxUkraine.
Does Banking Union Worsen the EU’s Democratic Deficit?
The need for greater supervisory data transparency
with Mark Hallerberg
Journal of Common Market Studies. 2015. 53(4): 769-785.
Download publication PDF.
When All is Said and Done: Updating 'Elections, Special Interests, and Financial Crisis'
with Mark Hallerberg
Research and Politics. 2015. 2(3): 1-9.
Download PDF.
Inflated Expectations: How government partisanship shapes bureaucrats' inflation expectations
with Cassandra Grafström
Political Science Research and Methods. 2015. 3(2): 353-380.
Download publication PDF or pre-publication PDF.
Write up on the Monkey Cage.
simPH: An R Package for Illustrating Estimates for Interactive and Nonlinear Effects from Cox Proportional Hazard Models
Journal of Statistical Software. 2015. 65(3): 1-20.
Download PDF.
R package simPH.
Letting German Banks Fail: Federalism and the decision to close troubled banks
with Sahil Deo, Christian Franz, and Mark Hallerberg
Politische Vierteljahresschrift (PVS). 2015. 56(2): 159-181.
Download publication PDF or pre-publication PDF.
Write up at the World Economic Forum.
Competing Risks and Deposit Insurance Governance Convergence
International Political Science Review. 2014. 35(2): 197-217.
Download: publication PDF or PDF proofs
Website with data, source code, and ancillary tables.
The Diffusion of Financial Supervisory Governance Ideas
Review of International Political Economy. 2013. 20(4): 881-916.
Download: publication PDF or pre-print PDF.
Download data and source code.
Other academic/policy publications
How not to create zombie banks: Lessons for Italy from Japan
with Mark Hallerberg
Bruegel Policy Contribution. March 2017.
Download PDF
Visualize Dynamic Simulations of Autoregressive Relationships in R
with Laron K Williams and Guy D Whitten
Download PDF.
The Political Methodologist. 2016. 23(2): 6-10.
Financial regulatory transparency: new data and implications for EU policy
with Mark Copelovitch and Mark Hallerberg
Bruegel Policy Contribution. December 2015.
Download PDF
Corrections and Refinements to the Database of Political Institutions’ yrcurnt Election Timing Variable
The Political Methodologist. 2015. 22(2):2-4.
Download PDF
Bad Banks in the EU: The impact of Eurostat rules
with Mark Hallerberg
Bruegel Working Paper. 2014/15.
Download PDF
Supervisory transparency in the European banking union
with Mark Hallerberg
Bruegel Policy Contribution. January 2014.
Download PDF
Media mentions: Der Standard (Austria)
Who Decides? Resolving Failed Banks in a European Framework
with Mark Hallerberg
Bruegel Policy Contribution. November 2013.
Download PDF
Also published in Nowa Europa (Poland).
GitHub: A tool for social data set development and verification in the cloud
The Political Methodologist. 2013. 20(2): 2-7.
Download the published PDF.
An updated PDF is available at SSRN.
Associated R package repmis.
Working Papers/Under Review
Speaking Under Stress: An Analysis of Federal Reserve Speeches
with Kevin Young
Download PDF.
Abstract
In this paper we analyze the ways in which the US Federal Reserve reacts to stressors in its economic and political environment by adapting its discourse when speaking to the public. We use a variety of quantitatively estimated indicators of the Fed’s economic and political circumstances and textual content analyses of Fed speeches from 1996 through 2012 to understand how pressures in the Fed’s political environment affect the topics they discuss when they meet and speak with outside groups. We find evidence that the Fed uses particular strategies to bolster its image as an apolitical and technocratic organization during periods of stress. We also find that some stressors were more important than others. Statutory measures of the Fed’s performance such as unemployment were not good predictors of the Fed’s discursive behavior, while structural conditions in the US economy, particularly declines in housing prices, were.
Predicting Self-Fulfilling Financial Crises
with Thomas Pepinsky
Download PDF.
Abstract
This paper studies how self-fulfilling dynamics affect the predictability of financial crises. We build a model in which market participants play an investment coordination game with common economic shocks and private information about their own willingness to cooperate. An observer attempts to predict the occurrence of a financial crisis in the future based on the players’ actions in the present. Under favorable conditions, good market conditions prevent an observer from learning about players’ types by observing their actions. This induces a negative correlation between economic conditions in the present and the variance of players’ types in the following period, which defines the predictability of financial crises. Under more extreme positive market conditions, the observer cannot use present observations of the players to learn about the probability of a financial crisis in the future. We test the implications of the model using a new continuous measure of financial market stress–“FinStress”–developed by Gandrud and Hallerberg (2015). We find support for a key implication of our theory: the variance of financial market stress is larger following periods of good economic conditions than following poor economic conditions. These conclusions have implications for both empirical analyses of the predictors of financial crises and for policymakers seeking to prevent crises. The findings in our paper suggest that regulators should focus on actors’ types (e.g. with stress tests) more than macro-economic conditions. More broadly, our analysis provides a new explanation for why social scientists and area specialists are generally poor at predicting events that require mass coordination, such as financial crises, coups, and revolutions.
Creating Scrutiny Indicators: A Change Point Exploration of Congressional Scrutiny of the US Federal Reserve
with Kevin Young
Download PDF.
Abstract
We investigate trends in Congressional scrutiny of the US Federal Reserve from the late 1990s through 2012. Though independent, the Federal Reserve (the Fed) is accountable to legislative principals. Our aim is to develop indicators of latent scrutiny from congresspersons’ behavior in committee hearings. These can be used to study the political stressors the Fed is under and how it responds. We use change point analysis to estimate periods of high and low legislative scrutiny from both the US House of Representatives and Senate. Surprisingly, though the Senate has the power to approve Fed appointments, their scrutiny of the Fed does not seem to noticeably change over our observation period. The House Committee on Financial Services did noticeably increase its scrutiny of the Fed during the recent financial crisis. The paper also introduces political scientists to new multivariate change point methods that can estimate latent legislative scrutiny states. These indicators could be used in future research to better understand legislative-bureaucratic relationships.
Bad Banks as a Response to Crises:
When Do Governments Use Them, and Why Does Their Governance Differ?
with Mark Hallerberg
Download PDF.
The project website.
Abstract
Many countries have used public asset management companies (AMCs, or “bad banks”) as part of strategies to restore their banking systems after crises. This includes the United States in the late 1980s, countries in East Asia and Latin America in the 1990s, and countries in Europe and Africa more recently. AMC structures, however, vary widely. Using a newly created global dataset of public bad banks, we begin to explore how domestic political institutions, international institutions, and international capital may be behind policymakers’ (a) decisions to create AMCs in response to crises as well as (b) design choices, particularly in terms of AMCs’ level of centralization. We find preliminary evidence that countries with low levels of reserves and many highly polarised veto players are more likely to create AMCs. We also confirm an important result from previous research that less democratic countries are more likely to create AMCs, but our evidence suggests that low levels of democracy may only affect decisions to create centralised AMCs, but not other types.
Clearing the Benches: How institutional incentives shape legislative brawls
with Emily Beaulieu
Abstract
From 1981 to present more than one hundred physical fights occurred in the parliaments of thirty-eight different countries around the world. While previous work has demonstrated that such breakdowns in legislative procedure are more likely to occur in younger democracies that have disproportionate electoral outcomes, here we argue that when they do occur, the electoral incentives of the actors involved should shape what the brawls themselves look like. Brawls that are used to enforce party loyalty should look different than brawls used to enhance personal reputations and in this paper we focus on how electoral incentives shape whether actors will prioritize party loyalty or personal reputation in their brawling behavior. Using detailed, original data on all legislative brawls since 1981 we offer a mix of quantitative and qualitative evidence to advance our claims.
Automating R Package Citations in Reproducible Research Documents
Download PDF.
Abstract
All of the R packages a reproducible computational research document relies on should be fully cited. Because R package syntax and capabilities change over time, if the versions used are not fully cited it will be difficult to actually reproduce the research that depends on them. In this short note, I introduce the LoadandCite command from the repmis R package. The command makes it much easier to document the R packages a piece of research depends on. If included in a dynamic reproducible research document, LoadandCite can (a) load all the R packages used to create the document, (b) create a BibTeX file that is updated every time the document is compiled with each loaded package’s full citation information. It also allows the user to install all of the packages, including specific versions. Using this command makes it easier to create really reproducible research with R.
Other
London School of Economics PhD Thesis. 2012.