<>
Nick said
I think you need to think about what you want here from an economics
point of view. You could aggregate or average multiple bonds in some
way. You could create some pseudo-time variable such that Stata will
still treat these data as panel data.
...
I would think that you might want to keep track of, for each country-
year,
(1) the number of debt issues (that is the number of duplicated
country-year records in your example), as an indicator of the
country's success in attracting investor / underwriter interest
(2) the total amount of debt issued per country-year
(3) the weighted average yield on the debt per country-year
(4) the weighted average tenor (term to maturity) on the debt per
country-year
The last two will take a bit of calculation, but these quantities may
easily be produced by -collapse- from your original data.
If you have bond prices rather than yields, then you could take the
weighted average price (although it would be cleaner to convert them
to yields first).
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/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
