Statalist


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

st: RE: re: temporal disaggregation - NOW -denton-


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: re: temporal disaggregation - NOW -denton-
Date   Wed, 29 Apr 2009 17:49:09 +0100

-denton- by Kit Baum is to be found on SSC. Just from reading its help quickly it's evident that it is based on the idea of summing subperiods to periods. Thus I'll bet that you should _not_ take logs first. 

Using two indicators is not allowed with -denton-. Presumably if you think you can do better with two indicators than one the way to approximate that is to try some combination, say a geometric mean or whatever makes economic sense. Or use -denton- twice with different indicators and see how far the results agree. That may inject the appropriate degree of uncertainty. 

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

Alice

I found this old post on the web that seems to help me on the question I sent yesterday - I need to interpolate GDP data from a quarterly to a monthly frequency.

I have downloaded the -denton- command and used it. I am however not sure my results are correct. I am using an index of industrial production as an indicator.

Shall I express GDP and industrial production in logs or not when using denton? Or are the results to denton independent of whether the variables are in logs or not?

Also, it appears that only one indicator can be used. Is there a way to use two different indicators?

<snip> 

*
*   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