Calibration of Ornstein Uhlenbeck Process

Main Page | Report this Page

Science Forum Index » Statistics - Math Forum » Calibration of Ornstein Uhlenbeck Process

Page 1 of 1

Author

Message

Guest

Posted: Thu May 01, 2008 12:11 am

Is it generally better to use a least square method or a maximum
likelihood method to calibrate an Ornstein-Uhlenbeck process from
historical data? The site

http://www.sitmo.com/doc/Calibrating_the_Ornstein-Uhlenbeck_model

gives an example of both options, but it's not clear which one is most
often adopted in practice.

Herman Rubin

Posted: Thu May 01, 2008 12:57 pm

Guest

In article <303576a0-67a8-4dd9-8c1a-38378d661e24@a23g2000hsc.googlegroups.com>,
<msmscarlatti@googlemail.com> wrote:

Quote:

The discretized version of an Ornstein-Uhlenbach model
is tha of a first-order Markov linear regression chain.
Maximum likelihood is a good process for this, with
asymptotic optimality, even if the "time" points are
not uniformly spaced. Maximum likelihood is definitely
better.
--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Department of Statistics, Purdue University
hrubin@stat.purdue.edu Phone: (765)494-6054 FAX: (765)494-0558

Page 1 of 1 All times are GMT - 5 Hours The time now is Wed Jul 09, 2008 10:22 am Science Forum Index