Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
re: Re: Re: st: gaps in the Hodrick-Prescott filter
From
Christopher Baum <[email protected]>
To
<[email protected]>
Subject
re: Re: Re: st: gaps in the Hodrick-Prescott filter
Date
Sun, 31 Oct 2010 16:22:15 -0400
<>
Elena said
Nick, Thanks. I had tried that yesterday and it works. Elena
On Sun, Oct 31, 2010 at 10:36 AM, Robert A Yaffee <[email protected]> wrote:
> Elena,
> You can use multiple imputation to impute the missing values.
> You may interpolate.
> Alternatively, you can set up a time variables such as
> gen time = _n
It works, but it is not appropriate unless your observations are evenly spaced in business-daily time (e.g. corresponding to each trading day, or each Wednesday, or whatever). If they are not, application of any standard time-series commands makes little sense--for instance, estimation of a first-order autocorrelation coefficient where the previous period might be one day or one week prior is not workable.
Kit
Kit Baum | Boston College Economics & DIW Berlin | http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming | http://www.stata-press.com/books/isp.html
An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/