Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: re: logistic function


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: re: logistic function
Date   Thu, 18 Jun 2009 23:49:21 +0100

I agree, naturally. But my only point is that for anyone who is thinking
"I need to invert the logistic", it is one natural Stata answer. 

Nick 
n.j.cox@durham.ac.uk 

Kit Baum

Nick pointed out invlogit(), which does not appear in the function  
list of density functions, but of math functions. Quite so, but it  
doesn't save much typing:

local cum1  1/(1+exp(-((_b[_cons]+ _b[trunk]*mut + _b[mpg]*mum +  
_b[d]*1) - mu)/s))

scalar onea = invlogit((_b[_cons]+ _b[trunk]*mut + _b[mpg]*mum +  
_b[d]*1 - mu)/s)

will indeed generate the same values, but you still have to compute mu  
and s and include them in the function argument.


In my prior example I had the line

gen d = (runiform()>0.7)

which did not appear in the posting.

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index