From "Nick Cox" To Subject st: RE: Root Mean Square Error and Pseudo R square....Please Help Date Mon, 27 Apr 2009 12:25:36 +0100

```What kind of pseudo R-square do you want? There are several.

Note that in your program, which seems uncannily familiar somehow, you
calculate z2, z3, z4 but never do anything with them. Depending on what
you want to do, that's a bug or a superfluity.

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

While performing the simulation for Probit model, how could we
calculate the RMSE and Pseudo R square? If it was OLS, we could just
use the formula and could do it in Excel but I could not use the
formula for Probit, since our Y is (0,1). There might be some code
that would help me find these. I would appreciate if anybody could
help me. My simulation so far looks like this. Could you please add
something in it?

.......................................Program..........................
..................................

global numobs 1000             // sample size N
global numsims "500"         // number of simulations
set seed 123456789

capture program drop endoprob

program endoprob // , rclass
version 10.1
drop _all
set obs \$numobs
generate u = rnormal(0)
generate mu = rnormal(0)
generate v = rnormal(0)
//generate x = rnormal(0)
generate z1 = rnormal(0)   // 4 Instruements
generate z2 = rnormal(0)
generate z3 = rnormal(0)
generate z4 = rnormal(0)
// Also be written *drawnorm u mu x1 z1 z2 z3 z4
generate a = 0.6*u

generate x = 0.5 + 0.9*z1 + a
regress x  z1 // endogenous regressor with four instruments
predict px

generate y = 0.5 + px + mu + u > 2    //Reduced Form Equation
ivprobit y (x= z1 )
predict py
end
simulate _b _se y py , ///
reps(\$numsims): endoprob

mean x* y*

*
*   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/
```