[R-sig-finance] Baxter-King filtering?

Andrew Piskorski atp at piskorski.com
Fri Nov 25 12:55:01 CET 2005

On Fri, Nov 25, 2005 at 07:03:40AM +0530, Ajay Narottam Shah wrote:
> A few weeks ago, Gabor showed this code for Hodrick Prescott
> filtering:

> The literature seems to think that Baxter-King works better. The idea

This paper:

  "A Frequency Selective Filter for Short-Length Time Series"
  by Alessandra Iacobucci, May 2004

compares the Hodrick-Prescott, Baxter-King, and Christiano-Fitsgerald
filters to his Hamming-windowed filter, and says that the
Hamming-windowed is best.

Andrew Piskorski <atp at piskorski.com>

More information about the R-sig-finance mailing list