REGRESION & STATISTICAL BANDS Ver. 1.00.a by @xel_arjona
Intro: This is an approach to get in one single indicator both of the best mathematical worlds in bands for technical analysis:
From within the STATISTICAL side, everybody well known the wide use of the STANDARD DEVIATION with a Multiplier Factor from within a Rolling Back MEDIAN (Simple Moving Average) best known as the famous and widely used "Bollinger Band".
From within the REGRESSION ANALYSIS side, the relevant importance of the STANDARD ERROR (of the estimate) with a Multiplier Factor from within an Ordinary Least Squares Curve generated from the last rolling back sample of the series. Jon Andersen use this method to construct it's Standard Error Bands.
Both indicators are in sync from a unique Rolling Back Period window. From this perspective, the Regression Analysis tend to "catch" faster moves and volatility while the Statistical band complement them perfectly for mid to long term move confirmation.
nice :D can also try cumulative average and deviation, for full historical deviation.
cum_price = cum(close)/(1+n)
cum_width = cum(abs(close-cum_price))/(1+n)
xel_arjona
⋅
Never heard of that approach! Do you have indicators with this methodology applied to study behaviour..? Thanks in advance @RicardoSantos !!!
Interesting toys..! -Griding- is a very intriguing topic to research on! Mr. W.D. Gann himself make a very big legacy to Technical Analysis on this field, but much of his work still remain as a mystery. Try to look out for this interesting book regarding this if you like: amazon.com/The-Square-Spiral-Trevor-Casey/dp/1921681438
cum_price = cum(close)/(1+n)
cum_width = cum(abs(close-cum_price))/(1+n)