Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: Simulation question


From   adiallo5@worldbank.org
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: Simulation question
Date   Thu, 3 Feb 2005 09:48:42 -0500

Ooops!
>>> I have in mind the case where a lot of dependent variables are involved.
I mean: independent.

Too busy or sleepy today.




                                                                                                                                           
                      adiallo5@worldbank.org                                                                                               
                      Sent by:                         To:       statalist@hsphsun2.harvard.edu                                            
                      owner-statalist@hsphsun2.        cc:                                                                                 
                      harvard.edu                      Subject:  Re: st: RE: Simulation question                                           
                                                                                                                                           
                                                                                                                                           
                      02/03/2005 09:22 AM                                                                                                  
                      Please respond to                                                                                                    
                      statalist                                                                                                            
                                                                                                                                           
                                                                                                                                           
                                                                                                                                           
                                                                                                                                           




Dear Marteen,

Thanks for the answer.
My question is precisely how to program Stata to find the best combination of
increases in POP and INVEST.
I have in mind the case where a lot of dependent variables are involved.
I was going around by doing it mechanically (i.e. raising one by one my
independent variables to approach the desired
result, but it's somewhat painful).
I think it's a matrice solving constraint equation. But as I said, I do not know
how to do this in Stata.

Amadou.





                      "Maarten Buis"

                      <M.Buis@fsw.vu.nl>               To:
<statalist@hsphsun2.harvard.edu>
                      Sent by:                         cc:

                      owner-statalist@hsphsun2.        Subject:  st: RE:
Simulation question
                      harvard.edu



                      02/03/2005 09:00 AM

                      Please respond to

                      statalist









Dear Amadou,

The easiest answer is that you do not need a simulation. The parameter of POP
tells you how much GDP will increase as a result of an unit increase in
population. So if the parameter of POP is .5 and GDP is 10, than an increase of
10 (doubling GDP) is achieved by and increase in the population of 20.

You could of course find a lot (infinite, actually) of combinations of increases
in POP and INVEST that will lead to a 10 point increase in GDP. So you will have
to make additional assumptions to narrow that down.

Beware of the assumed direction of causality: your model assumes that GDP is
caused by POP and INVEST, so doubling GDP causes nothing, but is caused by POP
and INVEST.

Hope this helps,
Maarten

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu]On Behalf Of adiallo5@worldbank.org
Sent: donderdag 3 februari 2005 14:32
To: statalist@hsphsun2.harvard.edu
Subject: st: Simulation question

Hi,

I have a simulation problem.

Usually, what I've seen done in simulations is to change
values in independent variables and see their result on the
(predicted dependent variable).

Ex:

reg GDP pop invest
predict gdphat
su gdphat
replace pop =pop * 1.03                                 /* 3% growth of
population*/
predict gdphat2
su gdphat2
g diff = gdphat - gdphat2                                   /*Measure of the
impact of the population growth */

Now, here is my question:

Suppose I want to double  my GDP ?
I am interested in how my independent variables will change (in their
coeffcients and/or in their observations ???)
to meet the new values of GDP.
I guess I am facing a constraint problem but do not know how to do this in
Stata.

How can I do that?

Best regards.

Amadou.

*
*   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/

*
*   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/




*
*   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/




*
*   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/



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