The function is correct.
The function normd() is the standard-normal pdf. That is, the normal
density with mean zero and standard deviation 1.
The function normprob() is the standard normal cdf, that is, the area
under the normal density from negative infinity to yhat.
Looking at these functions in Stata 9.2, it seems as though the density
function should be normalden(), while the distribution function should
be normal().
Hope this helps,
Justin Smith
On Wed, 16 Aug 2006 03:39:20 -0700 (PDT)
Nishant Dass <[email protected]> wrote:
JS>Dear List-members,
JS>
JS>I have the following question about Inverse Mill's Ratio:
JS>
JS>I run a probit regression for the selection equation and
JS>want to calculate the inverse mill's ratio.
JS>
JS>I found the following formula:
JS> gen imr = normd(y_hat)/normprob(y_hat)
JS>where "y_hat" is the fitted value from the probit equation.
JS>
JS>I tried searching for "normd" and "normprob" functions to
JS>see what this formula really does but couldn't find these
JS>functions in STATA Help.
JS>
JS>Could someone please confirm whether this is the correct
JS>formula for calculating the inverse mill's ratio? Thank
JS>you very much.
JS>
JS>Regards,
JS>
JS>Nishant
JS>
JS>__________________________________________________
JS>Do You Yahoo!?
JS>Tired of spam? Yahoo! Mail has the best spam protection around
JS>http://mail.yahoo.com
JS>*
JS>* For searches and help try:
JS>* http://www.stata.com/support/faqs/res/findit.html
JS>* http://www.stata.com/support/statalist/faq
JS>* http://www.ats.ucla.edu/stat/stata/
Justin Smith
PhD Candidate
Department of Economics
McMaster University
Phone: (905) 962-0353
E-mail: [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/
