I know that this has been tried in the past, but has anyone out there tried to use polynomial extrapolation to project Hurst channels? I've played around with curvilinear envelopes in the past but dismissed their usefulness and got rid of the Easy Language code. I'd like to re-evaluate the code but I can't seem to find it anymore. Does anyone out there have any polynomial regression code in Easy Language? -Hoo_doo
Thanks bgp, Unfortunately, I'm using TS2000i and the wealthlab code isn't much help to me at the moment. I may end up breaking down and witting the ez code myself. I just thought I'd check to see if anyone had any ez code for polynomials. -Hoo_doo
Ah ha! It's not exactly what I was looking for but it's very close none the less. Thanks once again to Clyde Lee. Here's the code if anyone is interested along with a screen shot... { Function: PolyFit_Proj } { Conversion: NumericalMethods FORTRAN to EasyLanguage Author of Conversion: Clyde Lee www.theswingmachine.com clydelee@swbell.net Permission to use copy distribute granted so long as credit for conversion is appended. } { PROGRAM LPOLYNOM} {C ----------------------------------------------------------------} {C Alg5"2.for FORTRAN program for implementing Algorithm 5.2} {C } {C NUMERICAL METHODS: FORTRAN Programs, (c) John H. Mathews 1995} {C To accompany the text:} {C NUMERICAL METHODS for Math., Science & Engineering, 2nd Ed, 1992} {C Prentice Hall, Englewood Cliffs, New Jersey, 07632, U.S.AX.} {C Prentice Hall, Inc.; USA, Canada, Mexico ISBN 0-13-624990-6} {C Prentice Hall, International Editions: ISBN 0-13-625047-5} {C This free software is compliments of the author.} {C E-mail address: in%"mathews@fullerton.edu"} {C } {C Algorithm 5.2 (Least Squares Polynomial).} {C Section 5.2, Curve Fitting, Page 278} {C ----------------------------------------------------------------} { SUBROUTINE SOLVELI(Price,NumPoint,AX,BX,DegPoly,CX) INTEGER Col,IX,JX,KX,DegPoly,IP,RX,Row,T REAL AX,BX,CX,XX,Price,PX,Sum,Pow,Prod,XK,YK,Err,Z1 DIMENSION AX(1:8,1:8),BX(1:8),CX(1:8),Price(1:53) DIMENSION Row(1:7),ZX(1:7) DIMENSION Pow(0:14) } Input: Price(C), {Price data to fit polynomial to and project } DegPoly(3), {Degree of polynomial to fit -- max=7 } ChanWidth(5), {Percent of price to setup for channel lines } {Negative = multiplier of 21 bar AvgTrueRange} NumPoint(25), {Number of data points to use in fit--max=53 } NPointPd(0); {Number of points forward to predict price } Input: EndDate(0); {Ending date for computation of coefficients } { SmoLeng(0); {Number of points in T3Average filter } } Array: CoefAry[12](0); Vars: EndKnt(0), IsEnd(False), HoldBar(0), ATR21(AvgTrueRange(21)), ChanWide(0), ChanMult(Iff(ChanWidth<0,-ChanWidth,ChanWidth*.01)); If EndKnt=0 Or IsEnd=False then Value1=PolyFit_Project(Price, DegPoly, NumPoint, NPointPd); IsEnd = Date>EndDate and EndDate<>0; If ChanWidth<0 then begin ATR21=AvgTrueRange(21); ChanWide=ATR21*ChanMult; End Else ChanWide=Average(c,51)*ChanMult; { If SmoLeng>0 then Value2=T3Average(Value1,SmoLeng) Else Value2=Value1; If SmoLeng>0 then begin Value2=Average(Value1,SmoLeng); Plot2[-NPointPd+IntPortion(SmoLeng/2+.5)](Value2,"CMA"); End; } If IsEnd and LastBarOnChart=False then begin If HoldBar=0 then HoldBar=CurrentBar; Value1=PolyFit_Project(Price, DegPoly, NumPoint, CurrentBar-HoldBar); Plot1[-(CurrentBar-HoldBar)-NPointPd](Value1,"EstPrice"); End Else If LastBarOnChart then begin If HoldBar=0 then HoldBar=CurrentBar; If EndKnt<MaxBarsForward then begin EndKnt=0; For Value2=0 downto -(MaxBarsForward-NPointPd) begin Value1=PolyFit_Project(Price, DegPoly, NumPoint, CurrentBar-HoldBar+EndKnt+NPointPd); Plot1[-(CurrentBar-HoldBar)-EndKnt-NPointPd](Value1,"EstPrice"); Plot2[-(CurrentBar-HoldBar)-EndKnt-NPointPd](Value1+ChanWide,"Est+C"); Plot3[-(CurrentBar-HoldBar)-EndKnt-NPointPd](Value1-ChanWide,"Est-C"); EndKnt=EndKnt+1; End; End; End Else begin Plot1[-NPointPd](Value1,"EstPrice"); Plot2[-NPointPd](Value1+ChanWide,"Est+C"); Plot3[-NPointPd](Value1-ChanWide,"Est-C"); End;