“Turning Points” in the Iraq Conflict

Abstract

The Harvard community has made this article openly available. Please share how this access benefits you. Your story matters AbstractWe consider and explore structural breaks in a day-by-day time series of civilian casualties for the current Iraq conflict: an undertaking of potential interest to scholars of international relations, Comparative and American politics. We review Bayesian change point techniques already used by political methodologists before advocating and briefly describing the use of reversible-jump Markov chain monte carlo techniques to solve the estimation problem at hand. We find evidence of four change points, all associated with increasing violence, approximately contemporaneous with some important state building events. We conclude with a discussion of avenues for future research.

The Structure of Appointment Politics: Consistency or Change?

“…Foreshadowing our later discussion, one obvious reason for this is structural changepoint analysis is a somewhat recent addition to the political science methodological toolkit (Park 2010; Spirling 2007a, 2007b; Wawro and Katznelson 2014), though the methods are older (e.g., Bai and Perron 1998, 2002; Barry and Hartigan 1993; Bhattacharyya and Johnson 1968; Chernoff and Zacks 1964). Regardless, establishing whether the appointment process has a singular underlying structure or has qualitatively changed is warranted.…”

“…Changepoint analysis allows uncovering underlying structural breaks without such a priori knowledge or increase in independent variables. Given these advantages, political scientists have used changepoint approaches to ascertain structural breaks in multiple contexts, including with reference to the determinants of American presidents' usages of force (Park 2010), executive orders (Bolton and Thrower 2016), Iraq War casualty rates (Spirling 2007b), campaign contributions (Blackwell 2018), Swiss initiative use (Leemann 2015), transnational terrorist kidnappings (Brandt, George, and Sandler 2016), and congressional voting patterns (Theriault 2013; Wawro and Katznelson 2014).…”

“…While such analyses generally adopted a Bayesian technique (Blackwell 2018; Hendershot et al 2013; Park 2010; Spirling 2007a, 2007b), especially in recent years, we employ the Zeileis, Hothorn, and Hornik (2008) model‐based recursive partitioning (MOB) method. This has several advantages over the Bayesian alternative.…”

Change-Point Detection and Regularization in Time Series Cross-Sectional Data Analysis

“…Change-point models have been widely used in applied work in political science such as the study of court(Hendershot et al 2013;Pang et al 2012;Park 2011a), terrorist attacks(Brandt and Sandler 2010;Santifort, Sandler, and Brandt 2013), congress(Smith et al 1999;Wawro and Katznelson 2014), civil war(Cederman, Gleditsch, and Wucherpfennig 2017), war casualties(Spirling 2007a), and international conflict(Nieman 2015).…”