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: st: RE: exponential smoothing
From
Robert A Yaffee <[email protected]>
To
[email protected]
Subject
Re: st: RE: exponential smoothing
Date
Mon, 16 Aug 2010 14:10:17 -0400
Lisa,
The double exponential imputes a trend that may be unwarranted by your data. Perhaps
you should try the simple exponential smoother.
Robert
Robert A. Yaffee, Ph.D.
Research Professor
Silver School of Social Work
New York University
Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2009.pdf
CV: http://homepages.nyu.edu/~ray1/vita.pdf
----- Original Message -----
From: Nick Cox <[email protected]>
Date: Monday, August 16, 2010 2:00 pm
Subject: st: RE: exponential smoothing
To: [email protected]
> Predicting the logarithm of sales and back-transforming is one
> possibility. Another is that your sales are fluctuating too
> erratically to be predictable by this method.
>
> Nick
> [email protected]
>
> Schöler, Lisa
>
>
> I want to do exponential smoothing for sales with Stata. I used the command
>
> .tssmooth dexponential sales = ussalesdols000, forecast(1)
>
> Sometimes I get negative out of sample forecasts which can't be true
> for sales. Is there a way to include a constraint so the out of sample
> forecasts will not get negative?
>
> *
> * 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/
*
* 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/