| Re: REGRESS with intercept 0 [message #58457] |
Thu, 31 January 2008 12:11 |
Vince Hradil
Messages: 574
Registered: December 1999
|
Senior Member |
|
|
On Jan 31, 12:45 pm, Violeta <v_sanj...@hotmail.com> wrote:
> Hello all
>
> I want to REGRESS x,y data and force the intercept to 0, and get
> errors measured with a 95 % confidence interval. I can't find a way to
> force the constant term to 0. My stats are a bit rusty and don't know
> how to retrieve chisq with a 95 % conf interval. Any comments would be
> very appreciated. Thanks
This is the thread: http://tinyurl.com/2bfhl9
Here's a nice summary: http://tinyurl.com/2aqlgx
|
|
|
|
| Re: REGRESS with intercept 0 [message #58460 is a reply to message #58457] |
Thu, 31 January 2008 11:07  |
Brian Larsen
Messages: 270
Registered: June 2006
|
Senior Member |
|
|
On Jan 31, 1:45 pm, Violeta <v_sanj...@hotmail.com> wrote:
> Hello all
>
> I want to REGRESS x,y data and force the intercept to 0, and get
> errors measured with a 95 % confidence interval. I can't find a way to
> force the constant term to 0. My stats are a bit rusty and don't know
> how to retrieve chisq with a 95 % conf interval. Any comments would be
> very appreciated. Thanks
I cant seem to find it this second, but there was a discussion about
forcing a fit through zero on the newsgroup recently, last 6 months
probably, spend some quality time with google on that.
I did remember this recent post about the confidence interval.
http://groups.google.com/group/comp.lang.idl-pvwave/browse_f rm/thread/877e06f061137953/62e34b355b7d786c?lnk=gst&q=re gression#62e34b355b7d786c
Cheers,
Brian
------------------------------------------------------------ --------------
Brian Larsen
Boston University
Center for Space Physics
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
