On Tue, Mar 26, 2013 at 4:32 PM, Nick Cox <njcoxstata@gmail.com> wrote:
> Good that you seem to be making progress.
>
> Just to comment on a side detail: I see no grounds for thinking that
> cloglog link implies a discrete response. In principle, it could make
> sense for continuous proportions too. As I recall, the original
> application (R.A. Fisher, no less) was for precisely this purpose.
I know Fisher invented the cloglog link, but I didn't know it was for
a continuous proportion. Yes absolutely it makes sense.
*
* 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/
