Trading Strategies Based On Digital Filters - page 75
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Hurst exponent
Simba..
I am glad that you responded, I thought that reference to a random walk would arouse a response from someone. I hope that I did not rouse your ire. Perhaps others will chime in with their arguments, I will only learn from them.
A month or so ago, I took your advice and read Hurst's book. I seem to remember his reference to the moon, but a quick rescan did not find it. Perhaps it was just my unconscious thought process as I read. I will read your other posts as time permits.
I am here to learn. A long time ago I learned that one cannot accept the word of authority without testing it. My skepticism has helped me avoid many pitfalls over the years, and has helped me to learn from the basics, not just on the surface. I do not say that the random walk model is correct. I just say that it can explain all the observed spectra that I have seen on this thread, or calculated myself using FX series. If you and RichCap are having success trading with the cyclic model, then that is evidence that the random walk model is not a sufficient explanation, or possibly evidence that you have a traders experience/intuition. I will continue to test the cyclic model using your suggestions.
Just to show why I am skeptical, let me show several images. First a random walk series, and the same series with a sinewave at period 160.
Now the spectrum of the random walk alone, using block length = 3*maxPer = 900, Standard Goertzel with fixed block length and end point flattening.
Finally the spectrum of the signal with the noise.
I find it hard to distinguish one from the other. How do you know when a signal is present?MadCow.
Several points I overview,involuntarily, in your post...
1-Your argument is biased,or better said,not fully developed.
You can post a few price series and,yes you can use Goertzel/MESA on both randomly generated price series and real ones and it will always return back some cycles...I already wrote that Goertzel`s major problem are the ghosts,so,obviously what you need first is to determine the degree of randomness in the series...
1-You analyze the time series with Hurst exponent and you will see if it is persistent,antipersistent or random...then you decide which strategy to use,cycles are a very good strategy for antipersistent series...tip..many pairs have a good timeframe(higher or = to H1) where you can find antipersistence,so,if you want to use cycles you use them in that timeframe....Cycles are very bad for random timeseries
..and there are better strategies to use in trends.
2-Regarding the analysis with Hurst exponent,I posted in this forum months ago-I believe it was in general discussion,thread "are markets random" or something similar-where we had very intelligent discussions with iGor and other members...At that thread I analyzed some member`s excel files,theorically similar (2) timeseries(1 real,1 randomly generated)...and,Man Hurst exponent did its job as fine as a snake oil salesman peddling his wares
....I will check for the link,if I find it,I will attach here....found
https://www.mql5.com/en/forum/178962/page6 the whole thread is worth reading,IMO....Specially this post I wrote nearly a year ago,where I hinted at what I am telling you now https://www.mql5.com/en/forum/178962/page6 .
3-Ok,now that trough the use of H exponent you know you have an antipersistent series...you still have a problem..Goertzel still gives you ghosts...so,reread both Richcap and mine later posts to you,each one of us gave you a method to filter out the ghosts,I explained how MTF analysis helps in finding the true cycles,and you reproduced those results using m30 and m1...Additionally the "long term" periods,aka the 40 and 56 periods nominal cycles present at h4 tf for practically all liquid pairs can help you frame the search-space...And Richcap explained,in his last words
... how to combine different methods of either spectral density estimation or freq analysis to eliminate (most of the ghosts)...Using Fourier and Goertzel will probably not add anything,because both methods are of the same family(Goertzel is just a simplified Fourier...and a better one to use in noisy environments),using Goertzel and MESA or Fourier and MESA will lead to better filtering out of the ghosts.
4-You can denoise the timeseries too,as Richcap said...I had always been a fan of denoising and detrending,on a conceptual standpoint...BUT,since I am an empiricist at heart,IMO,it is way better to use the raw prices,both close or H+L/2 will suffice....I can`t demonstrate it,it is just my experience,so,take this with a pinch of salt.
Conclusion:yes,We can be wrong with cycles,they are not perfect,so,the best way to stack the probabilities of being "right enough" for low risk high probability trades is:Apply them only to timeseries and timeframes whose H exponent says they are antipersistant...then use a combination of methods to filter out ghosts,then know that you are playing a probability game,so enhance it by using price action or trendline breakouts to trigger the actual entries...then spread your trades along a basket of uncorrelated/lowcorrelated pairs,use the right kind of money management...and that`s all.
P.S:I learnt long ago to disbelieve the experts,too...That is why I say to believe everything Hurst wrote,I tested it...and,of course,my suggestion would be for you to test it too...if you can get your hand on the 1600 pages Hurst course(Traderpress),his explanation of why you have to use trendlines to trigger the entries,no matter how many cycles are nested in your favour,is invaluable...The Course was written 30+ years ago,so the tools he used are outdated,but the way he uses them is the best teaching about how you can use actual tools like The Master,and ,an intelligent person like you have shown to be,won`t have any problem "translating" his methods to actual tools that are available today...You know,I believe that to succeed at trading you have to have a triple personality...1-a creative one,capable of embracing even the most "absurd" theories(ex:astrology)...2- a very critical one,to test and filter out the rubbish(I tested astrology patterns with a very sophisticated datamining program,I employed several months on the tests only,most of them are rubbish,a few of them have statistical validity)..3- a methodical,disciplined mind that can trade without deviations what he found and tested to be true,within a probability based realm....so,you need to be a dreamer,a critic and a manager ...In that order.
Regards
S
Simba.. Thanks for taking vacation time to help me out. I have begun to read the links you gave, and will try to be better informed as time passes. I apologize for repeating arguments already made by others, and refuted.
I'm new to this problem, and bring my communications engineering prejudices with me. I will undoubtedly lose some and retain others.
Your comments on preferable TF's seem to echo those of codebreaker in another forum. He suggests the use of False Nearest Neighbor analysis to find the best TF. Have you experience with this, or do you use the TF that has the best Hurst exponent ?
I was searching for the moon reference and came across a dusty old book that's been on my shelves since the '70's. "Cycles" by Edward R. Dewey. He used cycles to forecast the market in 1944, and his forecast was reasonably good until 1952. If you have not run across this book, it may be worth reading. His initial quote is typical of the book:
"By the law of Periodical Repetition everything which has happened once must happen again and again-and not capriciously, but at regular periods, ... the same Nature which delights in periodical repetition in the skies is the Nature which orders the affairs of the earth. Let us not underrate the value of that hint." -Mark Twain
Dewey,CB and other geniuses.
Simba.. Thanks for taking vacation time to help me out. I have begun to read the links you gave, and will try to be better informed as time passes. I apologize for repeating arguments already made by others, and refuted.
I'm new to this problem, and bring my communications engineering prejudices with me. I will undoubtedly lose some and retain others.
Your comments on preferable TF's seem to echo those of codebreaker in another forum. He suggests the use of False Nearest Neighbor analysis to find the best TF. Have you experience with this, or do you use the TF that has the best Hurst exponent ?
I was searching for the moon reference and came across a dusty old book that's been on my shelves since the '70's. "Cycles" by Edward R. Dewey. He used cycles to forecast the market in 1944, and his forecast was reasonably good until 1952. If you have not run across this book, it may be worth reading. His initial quote is typical of the book:
"By the law of Periodical Repetition everything which has happened once must happen again and again-and not capriciously, but at regular periods, ... the same Nature which delights in periodical repetition in the skies is the Nature which orders the affairs of the earth. Let us not underrate the value of that hint." -Mark TwainMadcow,
Think zen-like about the no timeframe-best timeframe...until you get your satori,use either best Hurst exponent tf or H4(USUALLY H4 tf is the one with best antipersistent H)...This will suffice.
Regards
S
Dear Simba,
You wrote that you use Wiz-Why software about to Forex.
Would you please to inform me how you can use it with real-time data? I have installed it but I do not see any option for using real-time data. I am going to try it out about Forex.
Thanks in advance.
Benjamin
K,
I will let Rich reply to you regarding his beautiful pics
,which,btw,seem to confirm that at H4 there is structure,but only for those that know how to look for it..while I will try to reply to your comments regarding h4,and finding optimal values..
1-You did 3 good predictions,I am not going to take into account that gbpusd didn`t go up,nor that eurusd stopped dead in its tracks and reversed,since you already explained that as a possibility,so,as I wrote before,your 3 "predictions" were good...You did those predictions using h4+h1..Now tell me,can you do any interesting prediction using m1?
2-Yes,the more bars sampled,the less error you have...WELL ONLY IF THE 2 DATASETS HAD EQUAL SIGNAL TO NOISE RATIOS PER BAR ..H4 is mostly signal,m1 is mostly noise,you are comparing pears with apples...AND,you just have enough apples at h4,so,use them...In any case I don`t care about convincing you,I just want the readers of this thread to take care,cycles below H1 have negative edge,you will lose money trading them.
3-Reality is reality,and theory is good in theory,but in practice,practice works better;)...more spaghetti for you(you lived 15 months in Italy so you must like them )A few weeks back you were obsessed with the optimal timeframe,reading CB thread,etc
..Now you are the Apostle of m1...but use H4+H1 to make your predictions..who understands you?I told you that time based the optimal timeframe is h4,all our tests with EAs show this...very simple..let`s presume best settings in h4 is 1 cycle slope from 30 to 60 periods...if we go to h1,1 cycle slope from 120 to 240 periods...it should be the same,or at least similar,isn`t it?It isn`t...or if we go to m15 it should be 1 cycle slope from 480 to 960 periods?..Again,it should be,but it isn`t...and,if you go UP to D1..from 5 to 10 days..again,it should,but it isn`t..what you will have is something like this(for the same period analyzed,let`s presume 1 January to date)and using the same cycle adapted to each timeframe...
H4=PF 5.10...H1=PF 2.30...M15=PF(0.80 to 1.61)...M5=PF (0.4 to 1.21)..D1=3.80
So,what is the optimal tf to trade?..The one that gets the best PF,Profit and %Drawdown in your tests,and ,at least with MESA and Goertzel based EAs,our tests show that the best tf is H4...Always,and second best is either D1 or H1...ALWAYS
Does this happens for all methods(Fibonacci,price action,etc)?NO...I use an israeli datamining program,WizWhy,it finds ALL patterns in the data,and I worked on pure price action patterns more than a year ago,you know extracting patterns like IF (C1>C2 & L1<L2<L3)Then BUY(Wizwhy tells you the rule`s probability and the error probability
..It is a beast)..well,I can tell you that for pure price action patterns,the best tf is D1,followed by W1.
So,the best timeframe-for your method-to trade is the one where your tests show the best results .
You know ,I am an empiricist at heart...
Your second question...regarding finding parameters,well,I think the reply is implicit in my previous words...Testing is necessary,not sufficient,because optimals do not exist in real Live trading,so,you need a "conceptual basis" that allows you to adequately frame your test results to be useful in the future..in the case of Rich,it can be,as his pics show,finding an alternate way to look at the problem to find the structure...in my case it was using MESA+SSA to find the stable cycles,then test them with EAs and confirm that they were indeed useful in practice.
Conclusion: Conceptual Frame+Extensive Tests= The Way to Go.
Regards
Simbadatamining
Dear Simba,
You wrote that you use Wiz-Why software about to Forex.
Would you please to inform me how you can use it with real-time data? I have installed it but I do not see any option for using real-time data. I am going to try it out about Forex.
Thanks in advance.
BenjaminBenjamin,
I don`t use with real time data,it works well with EOD data....so,I use it with EOD Data
I suggest that you don`t use it with below D1 data,because the patterns may not be so reliable...ANd,you have to do a lot of work to find the hidden patterns....
Regards
S
Dear Simba,
Thank you very much for your answer.
BR,
Benjamin
Benjamin,
I don`t use with real time data,it works well with EOD data....so,I use it with EOD Data
I suggest that you don`t use it with below D1 data,because the patterns may not be so reliable...ANd,you have to do a lot of work to find the hidden patterns....
Regards
Sis FullSSA_normalise.mq4 a replica of noxa cssa cycle for MT4???
in this case, Noxa cssa is just an Ergodic indicator repainting in his phase (?)
(Ergodic = less CPU eating)
Picture :
is FullSSA_normalise.mq4 a replica of noxa cssa cycle for MT4???
in this case, Noxa cssa is just an Ergodic indicator repainting in his phase (?)
(Ergodic = less CPU eating)
I think you have reconstructed Ergodic with SSA. That does not mean SSA = Ergodic. Your chart reminded me a post on NeuroShell forum where they used CSSA to emulate a windowed Hodrick-Prescott filter. I remade the chart. As you can see, CSSA emulates HP very well. I think we can emulate and even improve upon many existing indicators with CSSA/SSA by choosing the right bandwidth.
hello
how have i to use this indicator?goertzel
Custom indicator Steff
Hi there.
I need someone that can build a custom indicator for me please... I currently using a couple of indicators to trade and they work great as I've been trading profitable for months using these indicators. I would like to get them all on one or two indicator windows on my chart for space.
If your interested drop me a rep!!!