Replication Data for: What Happens Depends on When It Happens: Copula-based Ordered Event History Analysis of Civil War Duration and Outcome

Scholars are interested in not just what event happens but also when the vent happens. If there is dependence among events or dependence between time and events, however, the currently common methods (e.g., competing risks approaches) produce biased estimates. To deal with these problems, this article proposes a new method of copula-based ordered event history analysis (COEHA). A merit of working with copulas is that, whatever marginal distributions time and event variables follow (including the Cox model), researchers can derive whatever joint distribution exists between the two. Application of the COEHA model to a dataset from civil wars supports two controversial hypotheses. First, as wars become longer, rebel victory becomes more likely but settlement does not (there is dependence between time and events at both tails). Second, stronger rebels make wars shorter but do not necessarily tend to win, as experts predict but fail to establish (rebels' strength shortens time but has no effect on which events occur). Supplementary materials for this article are available online.

学者们不仅关注发生了何种事件，亦关切事件发生的时点。然而，若事件间存在依赖关系，抑或时间与事件间存在关联，当前主流分析方法（如竞争风险分析方法（Competing Risks Approaches））将得到有偏估计结果。为解决上述问题，本文提出一种基于Copula函数（Copula）的有序事件史分析（Copula-based Ordered Event History Analysis, COEHA）新方法。采用Copula函数的优势在于：无论时间与事件变量服从何种边缘分布（包括Cox模型（Cox Model）），研究者均可推导出二者间任意形式的联合分布。将COEHA模型应用于内战相关数据集后，验证了两项存在争议的假说。其一，随着战争持续时长增加，反叛武装获胜的概率逐渐上升，但停火和解的发生概率并未提升——即时间与事件在分布两端均存在关联。其二，实力更强的反叛武装会缩短战争时长，但未必会如学界专家所预测的那样更易获胜，而这一预测始终未得到实证支持——即反叛武装的实力仅会缩短战争时长，对最终发生的事件类型无任何影响。本文的补充材料可在线获取。