Which continuous-time model is most appropriate for exchange rates?
This paper determines the most appropriate ways to model diffusion and jump features of exchange rates. Simulations show that intraday periodicity in volatility prevents conventional tests from accurately identifying the frequency and location of jumps. We propose a two-stage correction for this periodicity that improves the properties of the test statistics. The most plausible model for 1-minute exchange rate data features Brownian motion and Poisson jumps but not infinite activity jumps. We also show that microstructure noise biases but does not unduly impair the statistical tests for jumps and diffusion behavior in finite samples.