Publication Type

Journal Article

Publication Date

3-2012

Abstract

In the last decade, intensive studies on modeling high frequency financial data at the transaction level have been conducted. In the analysis of high-frequency duration data, it is often the first step to remove the intraday periodicity. Currently the most popular adjustment procedure is the cubic spline procedure proposed by Engle and Russell (1998). In this article, we first carry out a simulation study and show that the performance of the cubic spline procedure is not entirely satisfactory. Then we define periodicity point processes rigorously and prove a time change theorem. A new intraday periodic adjustment procedure is then proposed and its effectiveness is demonstrated in the simulation example. The new approach is easy to implement and well supported by the point process theory. It provides an attractive alternative to the cubic spline procedure. © 2011 Elsevier B.V..

Keywords

Autoregressive conditional duration model; High-frequency data; Intraday periodicity; Nonstationary Poisson process; Point process

Discipline

Econometrics

Research Areas

Econometrics

Publication

Journal of Empirical Finance

Volume

19

Issue

2

First Page

282

Last Page

291

ISSN

0927-5398

Identifier

10.1016/j.jempfin.2011.12.004

Publisher

Elsevier

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Additional URL

http://doi.org./10.1016/j.jempfin.2011.12.004

Included in

Econometrics Commons

Share

COinS