On Tue, Nov 29, 2011 at 10:01 PM, G?rard Lochon <[email protected]> wrote:
> >
> > > Anyone know of a VFP friendly Least Square Regression Routine? Free is
> > > good.
> > >
Sorry for the delay:
LPARAMETERS tcTerms
lnLinest = 0
lnTotTerms = GETWORDCOUNT( tcTerms, [,])
IF lnTotTerms < 3
RETURN lnLinest
ENDIF
lnSx = 0.0
lnSy = 0.0
lnSy = 0.0
lnSxx = 0.0
lnSyy = 0.0
lnSxy = 0.0
= ALINES( laTerms, tcTerms, 1, [,])
lnCount = 0
FOR EACH lcTerm IN laTerms
lnCount = lnCount + 1
lnTerm = VAL( ALLTRIM( lcTerm))
lnSx = lnSx + lnCount
lnSy = lnSy + lnTerm
lnSxx = lnSxx + lnCount * lnCount
lnSyy = lnSyy + lnTerm * lnTerm
lnSxy = lnSxy + lnCount * lnTerm
ENDFOR
lnDet = ( lnSxx * lnTotTerms) - ( lnSx * lnSx)
lnA = ( ( lnSxy * lnTotTerms) - ( lnSy * lnSx)) / lnDet
lnB = ( ( lnSxx * lnSy) - ( lnSx * lnSxy)) / lnDet
lnMeanErr = 0.0
lnResidual = 0.0
lnCount = 0
FOR EACH lcTerm IN laTerms
lnCount = lnCount + 1
lnTerm = VAL( ALLTRIM( lcTerm))
lnMeanErr = lnMeanErr + ( lnTerm - ( lnSy / lnTotTerms))^2
lnResidual = lnResidual + ( lnTerm - lnA * lnCount - lnB)^2
ENDFOR
lnRR = 1 - lnResidual / lnMeanErr
lnSS = lnResidual / ( lnTotTerms - 2)
RETURN CAST( lnA as Numeric( 10, 5))
*!* ? [Slope = ] + TRANSFORM( CAST( lnA as Numeric( 10, 5)))
*!* ? [Y-Int = ] + TRANSFORM( CAST( lnB as Numeric( 10, 5)))
*!* ? [R = ] + TRANSFORM( CAST( lnRR as Numeric( 10, 5)))
_______________________________________________
Post Messages to: [email protected]
Subscription Maintenance: http://leafe.com/mailman/listinfo/profox
OT-free version of this list: http://leafe.com/mailman/listinfo/profoxtech
Searchable Archive: http://leafe.com/archives/search/profox
This message:
http://leafe.com/archives/byMID/profox/capuo4g7pfdn9ym0jjwbhbh15at2orfj6fi66odkizmsjy9c...@mail.gmail.com
** All postings, unless explicitly stated otherwise, are the opinions of the
author, and do not constitute legal or medical advice. This statement is added
to the messages for those lawyers who are too stupid to see the obvious.
