Measuring Arms: Introducing the Global Military Spending Dataset

Military spending data are used to measure key international relations concepts such as balancing, arms races, the distribution of power, and the severity of military burdens. Unfortunately, missing values and measurement error threaten the validity of existing findings. To address this challenge, we introduce the Global Military Spending Dataset (GMSD). The GMSD collates new and existing expenditure variables from a comprehensive collection of sources, expands data coverage, and, using a latent variable model, fills missing values and generates uncertainty estimates useful for assessing the severity of measurement error. In addition to validating the data, we present several new findings. First, correlations between economic and military power have not decreased, but increased over time. Second, we show historically that military burdens have been highest in Asia, not Europe. Finally, though military burdens fell for all regions over the past several decades, they remain high for the Middle East and Sub-Saharan Africa.

军事支出数据被用于衡量关键的国际关系概念，如平衡、军备竞赛、权力分配以及军事负担的严重程度。遗憾的是，缺失值和测量误差威胁了现有研究的有效性。为应对这一挑战，我们推出了全球军事支出数据集（GMSD）。GMSD整合了来自广泛来源的新旧支出变量，扩大了数据覆盖范围，并运用潜在变量模型填补缺失值，同时生成用于评估测量误差严重程度的不确定性估计。除了验证数据外，我们还提出了几个新的发现。首先，经济与军事力量之间的相关性并未随时间推移而降低，反而有所增强。其次，我们揭示了历史事实：军事负担最高的地区历来是亚洲而非欧洲。最后，尽管过去几十年所有地区的军事负担都有所下降，但中东和撒哈拉以南非洲的军事负担仍然居高不下。