DislikedI wanted to post a thought i had...
In rereading this post, CB you described your process as taking the OHLC stream, using the ULLMA on it, then doing a HA Calc, and finally smoothing it again with the ULLMA.
The OHLC you refer to i'm guessing is the "matched filter" OHLC that we create from the original OHLC ( pulling out the noise)?
Also, i may be doing something wrong....but on a 1hour time frame, i did the d{t} about 5 times, and was getting no closer to a valid t state....when you take the difference of a difference of a difference etc.....the # starts to get very big...please see my attachment..( i think i just used 5 min for the example...but in doing it with 1 hour data the dickey fuller was failing)...
cl
Thanks,
clIgnored