Vector Autoregression and the Study of Politics

Freeman, John R.; Williams, John T.; Lin, Tse-Min

doi:10.2307/2111112

Cited by 219 publications

(133 citation statements)

References 29 publications

Supporting

Mentioning

131

Contrasting

Unclassified

Order By: Relevance

“…For that reason, we need to look at multivariate time-series techniques, i.e., vector autogression (VAR). Vector autoregression involves the estimation of lags of different time series in the same equation (Sims 1980), and has been used in political science to study time series that interact with each other for several decades (Freeman, Williams, and Lin 1989). Our main innovation in this paper is to jointly fit a VAR and an IRT model so that the VAR can fully incorporate the measurement error present in the Twitter data.…”

Section: Modeling Ideological Polarization Over Timementioning

confidence: 99%

When Groups Fall Apart: Identifying Transnational Polarization with Twitter from the Arab Uprisings

Kubinec¹,

Owen²

2018

Preprint

View full text Add to dashboard Cite

Scholars continue to disagree as to what extent international social connections act as a conduit to influence contentious politics within states. To answer this question, we provide the first rigorous and real-time measure of transnational ideological diffusion across sectarian groups by employing a novel statistical method and new data to capture the transnational dynamics of polarization after the Arab Uprisings of 2011. As authoritarian governments fell, populations in several states polarized between secularists and Islamists over what kind of regime was to replace the ousted one. To examine these endogenous processes, we collected a comprehensive dataset on elite and citizen Twitter accounts in Cairo and Alexandria (Egypt) and Tunis (Tunisia) for a ten-month period during the critical year of 2013. Given the difficulty in directly measuring polarization, we also developed a new model, item response theory-vector autoregression (IRT-VAR), that allows us to incorporate measurement uncertainty while providing over-time estimates of transnational polarization. We show through our model that following catalytic events like regime ousters (such as the military coup against the Muslim Brotherhood in Egypt), we can separate the direct effects of these events on group polarization within a country from indirect transnational feedback happening through the channel of social media.

show abstract

Section: Modeling Ideological Polarization Over Timementioning

confidence: 99%

When Groups Fall Apart: Identifying Transnational Polarization with Twitter from the Arab Uprisings

Kubinec¹,

Owen²

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…It allows a researcher to specify a set of potentially causal variables in a predictive model without knowing the exact nature of the causal processes. A kind of 'everything-causes-everything' model that yields consistent time-series estimates (Freeman, Williams, and Lin 1989). It is particularly useful for forecasting how a change in one variable might lead to changes throughout the system if not feedback on itself.…”

Section: Vector Autoregressionmentioning

confidence: 99%

Anti-Immigrant Parties and Western European Society: Analyzing the Role of Immigration and Forecasting Voting

Breznau¹

2018

Preprint

View full text Add to dashboard Cite

This paper analyzes and predicts the trajectory of immigration and anti-immigration parties in Western Europe from 1962 to 2035. Immigration increased steadily until the 2000s when it reached unprecedented levels. By 2017, countries in Western Europe average 11% of votes cast for antiimmigrant parties. The percentage of the population that are first generation immigrants predicts between 50 and 94% of the variance in these votes across countries in Western Europe. Using methods of vector autoregression this paper analyzes the statistically causal role of immigration for predicting voting. Then using multilevel time-series models and qualitative cohort adjustments it forecasts both immigration and voting. Even the most conservative predictions suggest over 15% of the vote going to anti-immigrant parties by 2035. Given Europe's aging population and declining productivity, continued immigration to fill jobs among several segments of the labor market is necessary. This paper discusses the implications for the future of Europe drawing on theories of group dynamics and empirical research on politics and societies.

show abstract

“…In the econometrics and time series literature there are three generally accepted options for analyzing such a dynamic system: a) simultaneous equation models, b) (vector) error correction models and c) vector autoregressions. Freeman, Williams and min Lin (1989) and Brandt and Williams (2007) outline the relative tradeoffs in the selection of these models. A simultaneous equation specification requires the analyst to make assumptions about the (weak) exogeneity of the variables in the model.…”

Section: Empirical Approachmentioning

confidence: 99%

Democratic Accountability in Open Economies

Sattler

Brandt²,

Freeman

2010

QJPS

View full text Add to dashboard Cite

We analyze democratic accountability in open economies based on different hypotheses about political evaluations and government responsiveness. Specifically, we assess whether citizens primarily rely on government policies or if they focus on economic outcomes resulting from these policies to evaluate governments. Our empirical analysis relies on Bayesian structural vector autoregression models for the British economy, aggregate monthly measures of public opinion, and economic evaluations from . We find that voters continuously monitor and strongly respond contemporaneously to changes in monetary and fiscal policies, but less to changes in macroeconomic outcomes. Voters also respond to policies differently when institutions change. When the Bank of England became politically independent, citizens shifted their attention toward fiscal policy, and the role of monetary policy in their evaluations decreased significantly. Finally, politicians respond to voting behavior by adjusting their policies in a sensible way. When vote intentions and approval decrease, the government reacts to the public by adjusting fiscal policy and, before the Bank of England became independent, also monetary policy. * Earlier versions of this paper were presented at the Conference on the Political Economy of International Finance (PEIF), Federal Reserve Bank Atlanta, February 9, 2007, and the Seminar of the Center for the Study of Democratic Politics, Princeton University, October 25, 2007. Brandt's and Freeman's research was sponsored by the National Science Foundation under grants numbers SES-0351179, SES-0351205 and SES-0540816. Sattler's research was supported by the Swiss National Science Foundation under grant number 101412-101962/1. Harold Clarke kindly provided data on subjective personal expectations. We thank William Bernhard, Mark Hallerberg, Jude Hays, Tim Hellwig, Patrick Kuhn, David Leblang, Angela O'Mahony, Thomas Plümper, Dennis Quinn, Ken Scheve, the anonymous referees and the editors for comments. The authors are solely responsible for the contents. 1It is a fundamental idea of modern democratic politics that citizens evaluate their government and hold it accountable for its performance. Citizens can do this in different ways. In a recent, major contribution, Duch and Stevenson (2008) applied a competence model to this problem. They stressed the importance of outcomes, which are realizations of policies subject to random shocks and thus containing noisy signals about policymakers' competence. An alternative hypothesis is that citizens primarily evaluate policies that governments choose to draw conclusions about the quality of government decisions.We use an empirical framework that allows us to examine these hypotheses. It is based on a Bayesian structural vector autoregression model for the British economy, aggregate public opinion, and economic evaluations. We use this framework to examine the mechanism connecting observable and unobservable government policies, economic performance and citizens' evaluations of e...

show abstract

Vector Autoregression and the Study of Politics

Cited by 219 publications

References 29 publications

When Groups Fall Apart: Identifying Transnational Polarization with Twitter from the Arab Uprisings

When Groups Fall Apart: Identifying Transnational Polarization with Twitter from the Arab Uprisings

Anti-Immigrant Parties and Western European Society: Analyzing the Role of Immigration and Forecasting Voting

Democratic Accountability in Open Economies

Contact Info

Product

Resources

About