Thanks. All explaination here : http://www.mesasoftware.com/Papers/Ehlers%20Filters.exe
Also explained at the end of the paper : - KAUFMANÂ’S ADAPTIVE MOVING AVERAGE (KAMA) - VARIABLE INDEX DYNAMIC AVERAGE (VIDYA) To read, a very good synthetic parer, compilation of all Ehlers filter and even he rates them depending response and filtering power : http://www.mesasoftware.com/Seminars/TSWorld05.ppt - MAMA is interresting because it use Hilbert Transform and Cycle to adapt an EMA coefficient (coef alpha). http://www.mesasoftware.com/Papers/MAMA.exe I have coded it but i am not very impressed by the result (maybe comes that i find Hilbert Transform for Dominant Cycle to be not very powerfull). Maybe we can try an AR-AMA (Spectral AR frequency adapt the AMA coefs ? : ))) ) - Median-MA Difference, i never try this one ? someone got the AFL code or experience about it ? Cheers, Mich ----- Original Message ----- From: Paul Ho To: [email protected] Sent: Saturday, December 02, 2006 2:29 PM Subject: RE: [amibroker-ts] Re: Moving Average... one more again : ) Have you had a look at Ehlers filter or the zerolag filter Ehlers is at the http://www.amibroker.com/library/detail.php?id=402 Zerolag is as follows for(; i < nSize; i++) { float a = 2/(range[i] + 1); result.array[i] = a * (data[i] + beta * (data[i] - data[i -3])) + ( 1- a)* result.array[i - 1]; } It seems that CT3 is the smoothest, havent tried Adaptive Laguerre yet One way to deal with the lag, instead of shifting the averages back, shift the predicted line back, so the lag is dealt with by the prediction. Cheers Paul. ________________________________ _________________________________________________________________ Live.com: Le nouveau moteur de recherche par Messenger! http://www.windowslive.fr/livecom/
