DEFINITION OF DISTANCE FOR MARKED POINT PROCESS DATA AND ITS APPLICATION TO RECURRENCE PLOT-BASED ANALYSIS OF EXCHANGE TICK DATA OF FOREIGN CURRENCIES

Abstract

Recurrence plots are effective in analyzing nonstationary time series. Further, it is desirable to make the recurrence plot-based analysis applicable to marked point process data such as foreign exchange tick data. In this paper, we define a distance for marked point process data and establish the basis for further analyses. We also show that foreign exchange tick data have serial dependence using recurrence plots and the random shuffle surrogate method.