Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: RE: seasonal adjustment


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: RE: seasonal adjustment
Date   Mon, 11 Aug 2008 17:33:58 +0100

Hereabouts BEA means, or used to mean, British European Airways. It
presumably means something else near you, perhaps Bureau of Economic
Affairs.  

The FAQ advises against parochial allusions. 

On your main question, I think the answer is No. You can -findit
seasonal- to see what is available and nothing like X12 is evident to
me. 

I don't doubt that there are Stata users who would like to apply one or
more of these seasonal adjustment procedures in Stata, but they appear
highly unStataish to me, and it seems no surprise that there are no
Stata implementations. 

These procedures seem to be very complicated and relatively inflexible.
They tend to wire in arbitrary empiricisms and be very much of their
time. The idea that there is even a family of adjustment procedures that
will clean data regardless of (the rest of the) data generating process
seems not to march well with current time series ideas. Whenever I poke
around I tend to get the impression that only the source code would be
an adequate source for precisely what is being done, and that may not be
easily accessible. For these and yet other reasons I am not surprised
that no user-programmers have implemented any such. 

That still leaves open the question of why StataCorp haven't done it. I
can't answer on that except to comment that StataCorp developers too
have a detectable bias towards interesting projects and a bias against
tedious ones! Also, the problem with standard methods is that there are
so many to choose from....

More positively, quarterly data don't sound too awkward. You are free of
the messy calendar implications of weekends and when Easter fell. I will
ride my hobby-horse again that sines and cosines often do an excellent
job!

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

Galina An

Thanks for your suggestions, Nick,
the data is panel (quarterly in time-series direction, 36 quarters)  
and for each location, variables like construction, investment,  
marriage, exhibit quarterly seasonality, that needs to be removed.  
Unfortunately dummy usage does not remove much of that seasonality. Is  
there any procedure in Stata, like  X12 in e-views, that BEA uses to  
adjust for seasonality in national data series?

Quoting Nick Cox <n.j.cox@durham.ac.uk>:

> Your other posts indicate that you are an economist, although clearly
> your friend might not be.
>
> I think you'll need to specify more to get a really useful answer out
of
> the list.
>
> What kind of data?
> 	Length of series
> 	Resolution of series: daily, monthly, quarterly, other
>
> What kind of modelling exercise is in mind?
>
> Often in the Earth and environmental sciences Fourier series work very
> nicely to capture seasonality. In those fields seasonal rhythms are
> often interesting and important.
>
> In economics the classical point of view seems to be that seasonality
is
> a nuisance, and indeed the very term "seasonal adjustment" implies
that
> it is something that needs to be cleaned or corrected away, like dirt
or
> noise, before you can focus on what the economy is "really" doing.
>
> There does seem to be a slow but steady away from that to building
> seasonal components into models, but from a distance I can't sense any
> agreement on how best to do that, whether in terms of modelling the
> error or in terms of adding extra variables or both. Using dummy
> variables for quarters or months still appears to be popular. A key
> point is that does not need special technology in Stata. You just
create
> the dummies or use -xi- or something similar and then proceed with
your
> modelling command.
>
> Your friend, or other people interested in seasonality, may be
> interested in one or both of
>
> SJ-6-4  st0116  . . . .  Speaking Stata: In praise of trigonometric
> predictors
>         . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
N.
> J. Cox
>         Q4/06   SJ 6(4):561--579                                 (no
> commands)
>         discusses the use of sine and cosine as predictors in
>         modeling periodic time series and other kinds of periodic
>         responses
>
> SJ-6-3  gr0025  . . . . . . . . . . . . Speaking Stata: Graphs for all
> seasons
>         (help cycleplot, sliceplot if installed)  . . . . . . . . .
N.
> J. Cox
>         Q3/06   SJ 6(3):397--419
>         illustrates producing graphs showing time-series seasonality
>
> But my main point is that the question is too general to be likely to
> get a good answer.

Galina An

> Does anybody know a good seasonal adjustment procedure in 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/



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