在財務市場中，資產價格的跳點對於投資人資產配置以及風險管理策略有著重大的影響，因此價格跳點一直是個廣為被討論的重要議題，而不同的資產間出現的價格共跳對於投資人的避險策略更是有著重要的財務意涵，本篇文章提出了一個以迴歸為基礎的檢定，藉由利用高頻資料所計算出的Realized波動度來偵測資產價格中的跳點和共跳，這個檢定方式不僅能夠判斷價格序列中是否存在跳點，還能更進一步的判定跳點發生的時點。摸擬和實証結果都指出，這個以迴歸為基礎的跳點檢定改善了過去文獻中跳點檢定的過度警示問題，此外實証分析還証實了透過利用前瞻性資訊(forward-looking information)的使用，至少某比例的資產價格跳點具有顯著的可預測性。另一方面，我們將同樣的概念及分析方式運用在資產價格的共跳上，發現了其中不論是同向或是反向的共跳都存在著非對稱或是聚集的現象。Price jumps in financial markets have been a very important issue in Finance since it would distort the decision we make in asset allocation and risk management, not to mention the financial implications of co-jumps in hedging systematic risk. We propose a simple regression-based test for detecting jumps and co-jumps in asset prices utilizing the recent realized measures of variation in high frequency finance. The framework is informative in testing the existence of jumps, dating jump days, and quantifying jump contributions to price variations. Our suggested test improves the over-alarm detection of jumps from previous tests. Moreover, we also find evidence of predictable jumps, in particular with respect to proxy that contains forward-looking information. Generalizing the idea in testing for the implications of cojumps presented in realized covariance, we found asymmetry in both the frequency and magnitude among those downward or upward comovements.
