Re: Re: st: error correction model with quarterly data and dummies

[Christopher Baum <kit.baum@bc.edu>]

<>
On Dec 21, 2012, at 2:33 AM, Nick wrote:

> This is more a question about statistical style than about what is
> indubitably, indisputably, infallibly correct. My own preference is to
> consider the indicator variables (I recommend against "dummy" for
> reasons often mentioned on this list) as a team and to use them all,
> which here means three of them. To act otherwise is P-value fetishism
> in my view, but I imagine that you will find other views if you ask
> around enough.

I don't think this issue is a matter of personal taste or style. There is a qualitative factor, seasonality, and the set of dummies 
allows you to control for its significance. When you do that, you (or Stata) arbitrarily chooses one of them to exclude. 
The coefficients on the others are contrasts to the excluded class, and their 'significance' depends upon where the
 excluded coefficient's value is on the real line. Thus you should ALWAYS treat them, in Nick's words, as a team,
 and do a joint test for their significance. If you fail to reject the joint null, take them all out.
Otherwise, put them all in. Do not pick and choose.

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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/