More
importantly, Claude seems to have ignored my advice to read the FAQ on
his specific problem
http://www.stata.com/support/faqs/stat/rsquared.html
which calls into question why he is listing or exporting his data at
all. Seems more like he might want to
webuse grunfeld, clear
gen i1=(inv/kstock)>1
qui tab year, gen(dy)
cap xtprobit i1 k dy*, pa nolog
predict ihat if e(sample), mu
corr i1 ihat if e(sample)
di "Pseudo-R-sq is " r(rho)^2
cap xtprobit i1 k inv dy*, pa nolog
predict ih2 if e(sample), mu
corr i1 ih2 if e(sample)
di "Now Pseudo-R-sq is " r(rho)^2
though I fail to see the value of such an exercise.
On 12/19/06, Nick Cox <[email protected]> wrote:
Convergence will be much slower than you want if you reveal
your problems only slowly.
*
* 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/
