| |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Re: CES with nl
Rodolfo,
The formula in your program is different than the one that you wrote in the
description of the problem for us. Also, I didn't see how $e is identified.
Alwasy, it is a good idea to change the initial values for some numbers that
are feasible. The program below runs, for positive values of y, k, n and l.
Good luck, Rodrigo.
/// Modified CES
capture program drop nlces1
program define nlces1
if "`1'" == "?" {
global S_1 "a b c d"
global a=0.8
global b=0.5
global c=1
global d=1
global S_2 "CES with multiplicative error"
exit
}
replace `1' = ($a*($b*k^(-$c)+(1-$b)*l^(-$c))^($d/$c)+(1-$a)*n^($d))^
(-1/$d)
end
clear
set obs 100
drawnorm y n l k
replace y = y^2
replace n = n^2
replace l = l^2
replace k = k^2
nl ces1 y
/// End
----- Original Message -----
From: "Rodolfo Coelho Prates" <[email protected]>
To: <[email protected]>
Sent: Friday, June 08, 2007 9:09 AM
Subject: st: CES with nl
Dear listers,
I�ve tried estimate a nested CES production function with three factors:
capital (k), labor (l) and land (n).
The nested CES production function is:
y=e{a[bk^(-c)+(1-b)l^(-c)]^(d/c)+(1-a)n^d}^(-1/d)
I used nl command and wrote the follow instructions:
program define nlces1
if "`1'" == "?" {
global S_1 "e a b c d"
global a=1
global b=1
global c=1
global d=1
global e=.5
global S_2 "CES with multiplicative error"
exit
}
replace `1' =
$e*(($a*($b*k^(-$c))+(1-$b)*l^(-$c))^($d/$c)+(1-$a)*n^(-$d))^(-1/$d)
end
nl ces1 y
The Stata calculates the interections and print this message:
"cannot calculate derivatives"
What can I do?
Thanks a lot,
Rodolfo
*
* 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/