Re: extreme value

thierry wrote:
> hi,
> I'm working with a regression equation like : Y = - 2000 + 544*var1 +
> 1166*var2 - 487*var3.
> as you see, I have an intercept (-2000) negative, and it is due to extreme
> values on my data.
> what should I do ? ideally, I want to have a positive intercept. !!!!!!!!!
> Thank you.

Why do you "want" a positive intercept? By "want" do you mean
"expect"? If so, why? By "extreme" values, do you mean outlier
values of Y or values at the extreme ends of the ranges of your
independent variables (that isn't entirely clear to me)?

Cheers,
Russell
--
All too often the study of data requires care.

.

Relevant Pages

  • Re: extreme value
    ... as you see, I have an intercept negative, and it is due to extreme values on my data. ... Randomness comes in bunches. ...
    (sci.stat.consult)
  • extreme value
    ... as you see, I have an intercept negative, and it is due to extreme ... I want to have a positive intercept. ... Prev by Date: ...
    (sci.stat.consult)
  • extreme values
    ... as you see, I have an intercept negative, and it is due to extreme ... I want to have a positive intercept. ... Prev by Date: ...
    (sci.stat.edu)
  • Re: extreme value
    ... I've done business with companies that I thought should have to ... In cases where a reasonable argument can be made that an extreme ... tell you something (like the criteria for accepting customers ... > Thierry macon, ...
    (sci.stat.consult)
  • Re: multiple regression (intercept)
    ... thierry wrote: ... > is there any difference between regression equation with or without ... > I ask this question because I have a negative intercept in my equation (Y ... It is generally poor and incorrect practice. ...
    (sci.stat.math)
Loading