NATIONAL BUREAU OF ECONOMIC RESEARCH
NATIONAL BUREAU OF ECONOMIC RESEARCH

Telling from Discrete Data Whether the Underlying Continuous-Time Model is a Diffusion

Yacine Ait-Sahalia

NBER Working Paper No. 8504
Issued in October 2001
NBER Program(s):   AP

Asset returns have traditionally been modeled in the literature as following continuous-time Markov processes, and in many cases diffusions. Can discretely sampled financial rate data help us decide which continuous-time models are sensible? Diffusion processes are characterized by the continuity of their sample paths. This cannot be verified from the discrete sample path: by nature, even if the underlying sample path were continuous, the discretely sampled data will always appear as a sequence of discrete jumps. Instead, this paper relies on a characterization of the transition density of the discrete data to determine whether the discontinuities observed in the discrete data are the result of the discreteness of sampling, or rather evidence of genuine jump dynamics for the underlying continuous-time process. I then focus on the implications of this approach for option pricing models.

download in pdf format
   (823 K)

email paper

This paper is available as PDF (823 K) or via email.

Machine-readable bibliographic record - MARC, RIS, BibTeX

Document Object Identifier (DOI): 10.3386/w8504

Published: "Telling from Discrete Data Whether te Underlying Continuous-Time Model isa Diffusion" Journal of Finance, Vol. 57, pp.2075-2112 (2002) citation courtesy of

Users who downloaded this paper also downloaded these:
Andersen, Benzoni, and Lund w8510 An Empirical Investigation of Continuous-Time Equity Return Models
Piazzesi w8246 An Econometric Model of the Yield Curve with Macroeconomic Jump Effects
 
Publications
Activities
Meetings
NBER Videos
Data
People
About

Support
National Bureau of Economic Research, 1050 Massachusetts Ave., Cambridge, MA 02138; 617-868-3900; email: info@nber.org

Contact Us