<>
I would install -ssc d estout- and combine it with -capture-
*************
forval i = 1/184
{
capt eststo: nl (reward=y^{alpha=1}*{beta=0.6}*exp(-{r=0.1}*t)) if
id==`i'
}
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Quang Nguyen
Gesendet: Donnerstag, 7. Mai 2009 17:27
An: [email protected]
Betreff: st: How to solve this problem when running separate regression
using stasby or looping
Dear All,
I would like to run separate estimation equations for each individual.
Using the _stasby_ command such as:
statsby, by(id): nl (reward=y^{alpha=1}*{beta=0.6}*exp(-{r=0.1}*t))
Stata doesn't work since there missing value or inconvergence for some
individuals. Using the loop such as:
forval i = 1(1)184
{
nl (reward=y^{alpha=1}*{beta=0.6}*exp(-{r=0.1}*t)) if id==`i'
}
The same thing happens.
Can you suggest me a solution so that Stata can go on with the
estimation for all "estimable" individuals and assign missing value to
the case with inconergence or missing value?
Many thanks!
--
"My father gave me the greatest gift anyone could give another person,
he believed in me." - Jim Valvano
*
* 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/
*
* 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/
