Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: out-of-sample prediction does not work after -regress- with lags


From   maarten buis <maartenlbuis@googlemail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: out-of-sample prediction does not work after -regress- with lags
Date   Wed, 4 May 2011 17:26:21 +0200

On Wed, May 4, 2011 at 4:50 PM, Mirko <mirko.moro@gmail.com> wrote:
> I am not interested in the missing values at the beginng of the
> sample, clearly they are missing because there is not enough
> information. Instead, I would like to undestand why -predict- perfoms
> the out-of-sample forecast for one data point at the end of the series
> (the observations created with -tsappend-) only and not for the whole
> sample when lags are presents.

For your out of sample forcast you added five observations at the end.
By adding 5 extra years you did not also include the unemployment
rate for those years. After all, how could Stata know those? So the
unemployment rate for these years is missing, and Stata does not
know what to predict for these years.

Out of sample prediction is not black/white magic, it is just the filling
in of a formula. Your data must have information on all explanatory
variables to do an out of sample prediction, so just typing -tsappend-
will not do that (unless time is your only explanatory variable).

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------
*
*   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/


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