kelly johnson
> (2) I am using the stata -rolling- command (new to stata 9)
> to generate
> rolling correlations. if i declare my data set to be a time
> sereis dataset
> using the date variabe (format: %dD_m_Y) it doesn't work.
> however, when i
> use a new variable for observations (eg. like the one above,
> where it equals
> 1 for the first obs, 2 for the second observation, ...) and
> declare the data
> to be time series (tsset) on this variabel, it works. Why?
This question is very difficult to answer given the vagueness
of "doesn't work" and what you say about your dataset. However,
it sounds as if you have a problem. Using observation number
as time identifier amounts to an assumption that you
have consecutive observations. You should get equivalent
results with the real dates. Also, just in case you are not
aware of it, using the observation number as
time variable would certainly be incorrect if you have panel
data.
> (3) also, can you refere me to a good site where i can get
> more information on writing loops?
What kind of information?
Nick
[email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
