Quantcast

set seed

classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

set seed

sun samn


Hello, there,
     I do optimization ( actually is GMM). The calculation only works at the seed of '110110'. Otherwise, I get the error message-the initial value not feasible. If under the seed of 110110,  no matter what initial values I set, the value function does not converge--it ends at .914161. Does someone help me out with this?
Thanks a lot!

samn


     
_________________________________________________________________
Your E-mail and More On-the-Go. Get Windows Live Hotmail Free.
https://signup.live.com/signup.aspx?id=60969
*
*   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/
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

RE: set seed

Martin Weiss-5

<>
-set seed- is intended to make random number generation replicable. Where is
the random element in what you are trying to do? It would be better if you
could provide your code so listers can see for themselves.


HTH
Martin

-----Original Message-----
From: [hidden email]
[mailto:[hidden email]] On Behalf Of sun samn
Sent: Donnerstag, 20. Mai 2010 22:13
To: [hidden email]
Subject: st: set seed



Hello, there,
     I do optimization ( actually is GMM). The calculation only works at the
seed of '110110'. Otherwise, I get the error message-the initial value not
feasible. If under the seed of 110110,  no matter what initial values I set,
the value function does not converge--it ends at .914161. Does someone help
me out with this?
Thanks a lot!

samn


     
_________________________________________________________________
Your E-mail and More On-the-Go. Get Windows Live Hotmail Free.
https://signup.live.com/signup.aspx?id=60969
*
*   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/
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

RE: set seed

sun samn



Hello Martin,
   I attach the code for your reference. You can run it directly in stata with 'xtpqml' installed.
Thanks,
samn




> From: [hidden email]
> To: [hidden email]
> Subject: st: RE: set seed
> Date: Thu, 20 May 2010 23:06:33 +0200
>
>
> <>
> -set seed- is intended to make random number generation replicable. Where is
> the random element in what you are trying to do? It would be better if you
> could provide your code so listers can see for themselves.
>
>
> HTH
> Martin
>
> -----Original Message-----
> From: [hidden email]
> [mailto:[hidden email]] On Behalf Of sun samn
> Sent: Donnerstag, 20. Mai 2010 22:13
> To: [hidden email]
> Subject: st: set seed
>
>
>
> Hello, there,
>      I do optimization ( actually is GMM). The calculation only works at the
> seed of '110110'. Otherwise, I get the error message-the initial value not
> feasible. If under the seed of 110110,  no matter what initial values I set,
> the value function does not converge--it ends at .914161. Does someone help
> me out with this?
> Thanks a lot!
>
> samn
>
>
>      
> _________________________________________________________________
> Your E-mail and More On-the-Go. Get Windows Live Hotmail Free.
> https://signup.live.com/signup.aspx?id=60969
> *
> *   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/
     
_________________________________________________________________
Hotmail: Powerful Free email with security by Microsoft.
https://signup.live.com/signup.aspx?id=60969

test.do (4K) Download Attachment
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

AW: st: RE: set seed

Martin Weiss-5

<>



Attachments are not allowed on the list, even though the server apparently
makes exceptions from this rule from time to time. Let`s just say that you
do -generate- random numbers with the -rnormal()- function in there, so the
-set seed- command does have at least some kind of effect...



HTH
Martin

-----Ursprüngliche Nachricht-----
Von: [hidden email]
[mailto:[hidden email]] Im Auftrag von sun samn
Gesendet: Freitag, 21. Mai 2010 08:28
An: [hidden email]
Betreff: RE: st: RE: set seed




Hello Martin,
   I attach the code for your reference. You can run it directly in stata
with 'xtpqml' installed.
Thanks,
samn




> From: [hidden email]
> To: [hidden email]
> Subject: st: RE: set seed
> Date: Thu, 20 May 2010 23:06:33 +0200
>
>
> <>
> -set seed- is intended to make random number generation replicable. Where
is

> the random element in what you are trying to do? It would be better if you
> could provide your code so listers can see for themselves.
>
>
> HTH
> Martin
>
> -----Original Message-----
> From: [hidden email]
> [mailto:[hidden email]] On Behalf Of sun samn
> Sent: Donnerstag, 20. Mai 2010 22:13
> To: [hidden email]
> Subject: st: set seed
>
>
>
> Hello, there,
>      I do optimization ( actually is GMM). The calculation only works at
the
> seed of '110110'. Otherwise, I get the error message-the initial value not
> feasible. If under the seed of 110110,  no matter what initial values I
set,
> the value function does not converge--it ends at .914161. Does someone
help

> me out with this?
> Thanks a lot!
>
> samn
>
>
>      
> _________________________________________________________________
> Your E-mail and More On-the-Go. Get Windows Live Hotmail Free.
> https://signup.live.com/signup.aspx?id=60969
> *
> *   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/
     
_________________________________________________________________
Hotmail: Powerful Free email with security by Microsoft.
https://signup.live.com/signup.aspx?id=60969


*
*   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/
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

RE: AW: st: RE: set seed

sun samn

Hi Martin,
Right, I agree. But the problem is that the code does not work if the 'set seed' is off. Does this mean that there is something wrong with my code?
thanks!
samn



> From: [hidden email]
> To: [hidden email]
> Subject: AW: st: RE: set seed
> Date: Fri, 21 May 2010 09:23:20 +0200
>
>
> <>
>
>
>
> Attachments are not allowed on the list, even though the server apparently
> makes exceptions from this rule from time to time. Let`s just say that you
> do -generate- random numbers with the -rnormal()- function in there, so the
> -set seed- command does have at least some kind of effect...
>
>
>
> HTH
> Martin
>
> -----Ursprüngliche Nachricht-----
> Von: [hidden email]
> [mailto:[hidden email]] Im Auftrag von sun samn
> Gesendet: Freitag, 21. Mai 2010 08:28
> An: [hidden email]
> Betreff: RE: st: RE: set seed
>
>
>
>
> Hello Martin,
>    I attach the code for your reference. You can run it directly in stata
> with 'xtpqml' installed.
> Thanks,
> samn
>
>
>
>
>> From: [hidden email]
>> To: [hidden email]
>> Subject: st: RE: set seed
>> Date: Thu, 20 May 2010 23:06:33 +0200
>>
>>
>> <>
>> -set seed- is intended to make random number generation replicable. Where
> is
>> the random element in what you are trying to do? It would be better if you
>> could provide your code so listers can see for themselves.
>>
>>
>> HTH
>> Martin
>>
>> -----Original Message-----
>> From: [hidden email]
>> [mailto:[hidden email]] On Behalf Of sun samn
>> Sent: Donnerstag, 20. Mai 2010 22:13
>> To: [hidden email]
>> Subject: st: set seed
>>
>>
>>
>> Hello, there,
>>      I do optimization ( actually is GMM). The calculation only works at
> the
>> seed of '110110'. Otherwise, I get the error message-the initial value not
>> feasible. If under the seed of 110110,  no matter what initial values I
> set,
>> the value function does not converge--it ends at .914161. Does someone
> help
>> me out with this?
>> Thanks a lot!
>>
>> samn
>>
>>
>>      
>> _________________________________________________________________
>> Your E-mail and More On-the-Go. Get Windows Live Hotmail Free.
>> https://signup.live.com/signup.aspx?id=60969
>> *
>> *   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/
>      
> _________________________________________________________________
> Hotmail: Powerful Free email with security by Microsoft.
> https://signup.live.com/signup.aspx?id=60969
>
>
> *
> *   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/
     
_________________________________________________________________
Hotmail: Free, trusted and rich email service.
https://signup.live.com/signup.aspx?id=60969
*
*   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/
Loading...