Re: st: Re: Input data from keyboard combined with Monte Carlo

[John Antonakis <John.Antonakis@unil.ch>]

Thanks Joseph.

Seems that your suggestion fits the bill; however, I can't get it work.  
I have tried:

capture program drop sim
version 12.1
program define sim, rclass
syntax , data.dta(string)
drop _all

use "`data.dta'"

set obs 111

foreach var of newlist x1-x5 {
gen `var' = rnormal()
}
reg y x*

end

simulate explvar=e(r2), reps(50) seed(123): sim

Can you see where the problem is?

Best,
J.



__________________________________________

John Antonakis
Professor of Organizational Behavior
Director, Ph.D. Program in Management

Faculty of Business and Economics
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Switzerland
Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305
http://www.hec.unil.ch/people/jantonakis

Associate Editor
The Leadership Quarterly
__________________________________________

On 19.06.2013 13:40, Joseph Coveney wrote:
> John Antonakis wrote:
>
> Suppose that I want to run the below program.
>
> [omitted]
>
> Now I want to generate y by using fixed-values that I input, e.g.,
>
> input y
> [omitted]
> end
>
> How can I combine inputting the data within the MC program so that the
> y-values are always fixed and that the x's are randomly generated?
>
> 
--------------------------------------------------------------------------------
>
> You could do this by first putting in your fixed y-values in a Stata 
file, and
> then feeding the file name to your simulation program so that it can 
-use- it.
> I've shown an example of the approach below.  Although I've shown it 
using a
> permanent file in the present working directory, my suggestion is to use
> -tempfile- if it's possible.  If your -tempfile- directory has spaces 
in the
> path, then be sure to surround it with double quotation marks.
>
> Joseph Coveney
>
> version 12.1
>
> clear *
> set more off
>
> program define sim, rclass
>     version 12.1
>     syntax , file(string)
>
>     drop _all
>     use "`file'"
>     foreach var of newlist x1-x5 {
>         generate double `var' = rnormal()
>     }
>     regress y x*
> end
>
> /* Now I want to generate y by using fixed-values that I input */
>
> input y
> 4.715581
> 4.296504
> 4.170745
> 2.065717
> 3.648136
> 8.156727
> 2.280866
> 2.817171
> 2.647611
> 3.272532
> end
>
> quietly save myfile
>
> simulate explvar=e(r2), reps(50) seed(123): sim , file(myfile)
> list in 1/5, noobs separator(0)
>
> /* Now I want to generate y by using fixed-values that I input, Take 2 */
>
> drop _all
> input y
> 0.8089706
> 0.7720405
> 1.9218385
> 0.58947305
> 1.5778341
> 0.5398982
> 1.142306
> 0.50413711
> 0.23358981
> 0.24074392
> 0.6785751
> end
>
> quietly save myfile, replace
>
> simulate explvar=e(r2), reps(50) seed(123): sim , file(myfile)
> list in 1/5, noobs separator(0)
>
> erase myfile.dta
>
> exit
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/