Closely spaced change-point detection with an application to geopolitical shocks in oil and gas markets
Change points that arrive in quick succession, or near the boundaries of the sample, are prone to type-II error: the few observations trapped between successive breaks carry too little information for global procedures to analyze. This article develops a test statistic, $I_1$, for which we derive the limiting null distribution under Gaussian noise, extend the theory to weakly dependent sequences, and prove consistency under a mean-shift alternative. Around $I_1$, we construct DCI, a two-phase algorithm that couples a global scan with multiple local tests via an adaptive-width sliding window. In extensive simulations, $I_1$ and DCI remain Pareto-optimal over criteria spaces spanning true and false positive rates, localization error, and segmentation covering. An application to the US-Iran 2026 conflict quantifies the exposure of energy markets to geopolitical shocks using two new metrics, event sensitivity and event attribution, leading to time series tokenization.