MathGroup Archive 2005

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: regress versus fit - force through zero/force constant term to zero

  • To: mathgroup at smc.vnet.net
  • Subject: [mg61521] Re: regress versus fit - force through zero/force constant term to zero
  • From: dh <dh at metrohm.ch>
  • Date: Fri, 21 Oct 2005 00:38:04 -0400 (EDT)
  • Sender: owner-wri-mathgroup at wolfram.com

Hi Chris,
I stumbeled myself over this behaviour of Regress.
Here is an excerpt from the Help of Regress:

Two of the options of Regress influence the method of calculation. 
IncludeConstant has a default setting True, which causes a constant term 
to be added to the model even if it is not specified in the basis 
functions. To fit a model without this constant term, specify 
IncludeConstant -> False and do not include a constant in the basis 
functions.

Daniel

Chris Chiasson wrote:
> Hi MathGroup,
> 
> If I have:
> <<Statistics`LinearRegression`
> FAASCalPts={{1,0.032},{2,0.067},{5,0.183}}
> FAASCalFit=Fit[FAASCalPts,{cCaPos},cCaPos]
> FAASCalRegression=
>   Regress[FAASCalPts,{cCaPos},cCaPos,
>     RegressionReport\[Rule]{SummaryReport,BestFit}]
> 
> I expect the answer from Fit, but not the one from Regress. Regress
> seems to be ignoring the fact that I only want the first order (and
> not the zero/constant order) term.
> 
> How do I obtain fit diagnostics if I am forcing a 0 for the constant order?
> 
> Thank you,
> --
> Chris Chiasson
> http://chrischiasson.com/contact/chris_chiasson
> 


  • Prev by Date: Re: Re: Map Thread & Inner
  • Next by Date: Re: Re: Re: DSolve and matrix form of system of equations
  • Previous by thread: Re: regress versus fit - force through zero/forceconstant term to zero
  • Next by thread: ListSurfacePlot3D