Talk:Seasonal adjustment

Improvements to this page
I am user statsfoar and I work for the Office for National Statistics. I have been looking into improving this page on seasonal adjustment.

The main changes I would like to make are as follows:

1. To modify the introduction. I would like to update one of the links to the original source. I would like to simplify the definition for seasonal adjustment. I would like remove the second sentence and first link and add it to the ‘Example’ section. I would like to include a graph of one of the examples mentioned in sentence three.

2. To modify the section ‘Time series components’. I would like expand briefly on each component, stating in turn what each is. I would like to add a small section on decomposition of a time series and add graphics to aid interpretation.

3. To modify the section ‘Seasonal adjustment’. I would like to incorporate calendar related effects such as Easter and trading-day. I would like to remove the second paragraph and add it to a new section (Methods and Software). I would like to include the second paragraph from the section ‘Example’ including advantages and disadvantages of year on year comparisons and other methods.

4. To create a new ‘Methods and Software’ section. This will include the second paragraph of the ‘Seasonal adjustment’ section with a few updates. I would also like to include a simplified overview of the X-11 algorithm, State Space Modelling and SEATS approach with links to more detailed sites.

5. To modify the section ‘Example’ to include more real life examples, such as the retail sales index. I would like to include the corresponding time series graphs to aid interpretation. I would like to remove the second paragraph and add it to the section ‘Seasonal adjustment’.

6. To update the section ‘Moves to standardise seasonal adjustment processes’.

7. Update to include links to current software.

If there are any issues with any of my proposed changes or if you would like any more detail on what I intend to do, I am happy to discuss.

Statsfoar (talk) 09:58, 9 June 2014 (UTC)

Examples?
Might we get some examples of the seasonal influences that make adjustment necessary? — Preceding unsigned comment added by 76.4.83.206 (talk) 20:35, 13 October 2011 (UTC)

Use of SA data in regression
I did a quick check of the statement and found that the regression coef would NOT change if you SA first and then regress, or regress along with dummy factors. So this seriously needs some reference, or it should be deleted.

If X is your seasonal dummy, Z is independent variable and Y is response, then the coef on Z is always $$(Z^T (I-P)Z)^{-1}Z^T(I-P)Y$$, with $$P=X(X^TX)^{-1}X^T$$, no matter which order you did SA. --31.221.13.140 (talk) 12:15, 25 April 2013 (UTC)

External links modified (January 2018)
Hello fellow Wikipedians,

I have just modified 3 external links on Seasonal adjustment. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:
 * Added archive https://web.archive.org/web/20110720161129/http://circa.europa.eu/irc/dsis/eurosam/info/data/demetra.htm to http://circa.europa.eu/irc/dsis/eurosam/info/data/demetra.htm
 * Added archive https://web.archive.org/web/20111018232034/http://www.cros-portal.eu/page/seasonal-adjustment to http://www.cros-portal.eu/page/seasonal-adjustment
 * Added archive https://web.archive.org/web/20101117151240/http://epp.eurostat.ec.europa.eu/cache/ITY_OFFPUB/KS-RA-09-006/EN/KS-RA-09-006-EN.PDF to http://epp.eurostat.ec.europa.eu/cache/ITY_OFFPUB/KS-RA-09-006/EN/KS-RA-09-006-EN.PDF

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

Cheers.— InternetArchiveBot  (Report bug) 03:46, 26 January 2018 (UTC)