Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: HP Filter Weights -- Integers Only!?!


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: HP Filter Weights -- Integers Only!?!
Date   Sat, 9 Oct 2004 18:27:48 +0100

I guess you're referring to -hpfilter- as 
published in STB-17. 

The Statalist FAQ includes this advice: 
"Say what command(s) you are using. 
If they are not part of official Stata, 
say where they come from: the STB/SJ, 
SSC, or other archives."

What you _could_ do is copy the program 
file to another file, edit the program 
name in the -program- statement to be consistent, 
and change the line 

	local options "Lambda(int 1600) Suffix(str)"

to 

	local options "Lambda(real 1600) Suffix(str)"

But then you've created a program for which 
you should take responsibility. Among other 
things, -hpfilter- as originally published 
in the STB is set up on this basis: the 
variable is assumed to be sorted on time 
or some other ordering variable, which is 
taken to come equally spaced, but this is not really
explained in the documentation. This may well 
match your data, but watch out. 

Nick 
n.j.cox@durham.ac.uk 

Uwe Berberich
 
> I would like to filter output-series using the HP-filter. I thought 
> about using 6.25 as the HP-weight for my annual data -- as 
> proposed by 
> RAVN und UHLIG (Review of Economics and Statistics, 2003). 
> Unfortunately, --hpfilter-- only allows *integers* for the HP-weight.
> Does anyone know about a way to use the exact weight of 6.25?

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index