Wavelet Transform: Wavelet Denoised & Residual Indicator
Example 1. The indicator displaying a filtered price series and a residual term of wavelet transformation:
In the Figure above one can see that the wavelet filtration (the red line) deletes outliers on non-trending periods but leaves the prices on trend periods the same. Also the residual term of wavelet transformation can be used similarly to long-term moving average.
| EasyLanguage: |
{********************************************************
Non-decimated Haar Wavelet Denoised & Residual Indicator
Copyright (c) Trade Smart Research Group 2002
Notes: The math is based on Multiresolution Analysis of Time Series
www.multiresolutions.com
********************************************************}
Inputs: Price(Close), {a price series}
Scales(6), { number of scales }
NSigma(2); { threshold value signal / noise}
vars: Lookback(0), count(0); { definition of variables }
Array: ArrayPrice[511](0); {definition of Array}
defineDLLFunc: "tswvl.DLL", FLOAT, "RUNWVL",LPFLOAT,int,float; {definition dll}
defineDLLFunc: "tswvl.DLL", FLOAT, "GETALLVALUES",int,int;
lookback = power(2, Scales); {calculation of quantity of elements of a Array}
for count = 0 to lookback -1 begin
ArrayPrice[count] = Price[count]; {the task of elements of Array}
end;
Value1 = RUNWVL(&ArrayPrice[0],Scales, NSigma); {the smoothed series}
Value2 = Scales + 1;
Value3 = GetAllValues(3, value2);
Plot1(value1, "Denoised"); {drawing of charts}
Plot2(value3, "Residual");
|
|
