I would guess that the easiest way to
get at this is as partial correlations
calculated from the ranks of the variables,
given that Spearman(y,x) = Pearson(rank(y), rank(x)),
using non-standard but I hope transparent
notation.
However, that still leaves unsolved the
whole question -- if it is interesting to
you -- of attaching a P-value that respects
the panel structure of your data, and particularly
its time dependence. For that and other reasons,
partial correlation is likely to prove a dead
end for you, and a regression-based approach
may be more fruitful.
Nick
[email protected]
Martial Foucault
> I wish to calculate some partial rank correlation coefficient
> after have
> calculated Spearman rank correlation coef.
> But I did not found on Stata 8 the corresponding command.
> Many thanks a
> lot for your help. My data set is cross section pooled data.
*
* 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/
