st: RE: Saving simulation runs

[Nick Cox <n.j.cox@durham.ac.uk>]

This looks confused to me. 

What e(b) are you expecting to be lying around after -simulate-? It seems to me that at most you could expect just the _last_ e(b) from the -regress- within your -sim- that -simulate- is calling, i.e. in this example just the 100th of 100 calls. The other 99 incarnations of e(b) will have disappeared. 

As to why this is no longer working, my wild guess is that you seeing a consequence of the change to -clear- in 11.0, which is documented in -help whatsnew10to11- and [U] 1.3. 

In fact I doubt that this ever worked as you intended; it just gave results that looked OK to you. One key aim of -simulate- is to manage storage of results; it's not necessary to do much management yourself. 

Re-reading the help for -simulate- is one possibility. 

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

John Antonakis

My code here, which seemed to work fine before, stopped working (I am 
sure that I did not change it, though can't find anything wrong with it).

***************************************
clear
capture program drop sim
  version 11.1
program define sim, rclass
         drop _all
syntax , nobs(integer )
set obs `nobs'

gen x1 = rnormal()
gen x2 = 2*x1 + .1*rnormal()
gen y = x1 + x2 + rnormal()
reg y x1 x2
end

mat b=e(b)
mat save = b

foreach nobs of numlist 100(100)1000 {
simulate _b _se, reps(100) seed (123) : sim, nobs(`nobs')
mat b=e(b)
mat save = save \ b
}

mat list save
***************************************

Also, how would I save the mean of the standard errors, along with the 
mean of the coefficients, from each of the monte carlo runs?


*
*   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/