[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [amibroker] Re: Walk-Forward Testing (was question/ help)



PureBytes Links

Trading Reference Links




Pal:
 
Sorry, but I changed the title to something that can be searched on. 
Anyway, I write this because I read with interest an idea that I believe Chuck 
expressed this morning in an unrelated post. Suppose your watchlist is composed 
of, say, the Nasdaq 100 (N100) (it could be anything; this is just an example). 
Divide the N100 stocks into 2 50-stock watchlists by randomly selecting 50 
stocks from the N100 for each watchlist. Then, do your development/optimization 
on one of the 2 watchlists for 1999 to Dec 2003 (present time). Then, use the 
optimized parameters plus the OTHER watchlist for your "walk-forward" 
testing. This way, you use the entire date range but you test the system's 
validity or robustness on another watchlist that has never seen the parameters 
or the system at all. If the system performs as well or better on the second 
watchlist as it did on the one used for the optimum parameters, then you may 
conclude you have a tradeable system. I'd like to hear others' opinions as to 
the validity of this approach. Any thoughts?
 
AV
<BLOCKQUOTE 
>
  ----- Original Message ----- 
  <DIV 
  >From: 
  palsanand 
  
  To: <A title=amibroker@xxxxxxxxxxxxxxx 
  href="">amibroker@xxxxxxxxxxxxxxx 
  Sent: Saturday, December 13, 2003 5:38 
  PM
  Subject: [amibroker] Re: question/ 
  help
  I would point you to the following article:Walk 
  Forward Tested System Is Better than the BestOptimized One - Larry 
  WilliamsIt looks like the history of technical analysis has been 
  largely influenced by optimization. That is, we studied the past, found 
  something that looked significant, then optimized rules and procedures 
  to trade the observation in the future.Sometimes that has worked. 
  Often it has not. That's our dilemma. What are we to do? In the past, we 
  answered these questions by doing more optimization, more curve fitting. 
  Indeed, we treated historical data like prisoners of war. Our thesis was, 
  if you beat them often enough they would reveal anything. Which is true, 
  but you want them to reveal everything, not anything.This brings 
  me to one point. I think we will all make much more headway with system 
  development by spending less time on optimization and more time on walking 
  systems and procedures forward.If on a walk forward test, the system 
  holds up, we probably have something. And for sure, what we have will be 
  better than the very best optimized system when it comes to real time 
  trading. Hence, let's see what we can learn from each other about 
  conducting walk forward tests. Any ideas will be appreciated by all, I am 
  certain - L.W.It's certainly correct that if done properly, walk 
  forward testing has great value. For those of you not aware of walk 
  forward testing, it's first setting your system parameters and then 
  testing the results in the future using those pre-set parameters without 
  benefit of additional or new optimization (re-optimization). Some people 
  refer to that as "hypothetical real-time trading."However, walk 
  forward testing can in fact be a trap if done incorrectly. That's because 
  there's a problem in deciding what pre-set algorithm or parameters to use 
  prior to the so-called walk forward test. If we arrive at those parameters 
  by an optimization process, then we may be guilty of optimizing the walk 
  forward test without even realizing we have done that. Another pitfall, is 
  the great tendency to optimize the walk forward testing time period 
  itself.Possibly the only way to do it correctly, is to first 
  arrive at a set of parameters and algorithm based on logic, experience, or 
  sound trading principles that won't be subject to change. Then do a walk 
  forward with no attempt to improve results via re-optimization.A 
  robust system is one that uses the least amount of parameters and still 
  has a good chance of being profitable in the future with atleast 30 
  trades/year to be statistically significant with the in-sample testing 
  period of atleast say, 15 years to minimize the possibility of chance or 
  chance alone being responsible for the excellent results - 
  Palrgds, Pal--- In amibroker@xxxxxxxxxxxxxxx, "goldwing01" 
  <GOLDWING01@xxxx> wrote:> Has any tried using databull for 
  downloading data, it seems to look > better than yahoo or a least 
  relieving yourself from the stress of > downloading problem.> 
  > Next question, optimization, why do I need to optimize my data and 
  > when should I optimize my data > > Next question, I 
  would like to have one screen to constantly look at > ^IXIC and 
  another to move as I point and click at other symbols can > someone 
  help with this please.
  Send BUG REPORTS to bugs@xxxxxxxxxxxxxSend SUGGESTIONS to 
  suggest@xxxxxxxxxxxxx-----------------------------------------Post 
  AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx (Web page: <A 
  href="">http://groups.yahoo.com/group/amiquote/messages/)--------------------------------------------Check 
  group FAQ at: <A 
  href="">http://groups.yahoo.com/group/amibroker/files/groupfaq.html 
  Your use of Yahoo! Groups is subject to the <A 
  href="">Yahoo! Terms of Service. 
  
<BLOCKQUOTE 
><FONT 
  face="Courier New">---Outgoing mail is certified Virus 
  Free.Checked by AVG anti-virus system (<A 
  href="">http://www.grisoft.com).Version: 6.0.543 
  / Virus Database: 337 - Release Date: 
11/21/2003






Yahoo! Groups Sponsor


  ADVERTISEMENT 









Send BUG REPORTS to bugs@xxxxxxxxxxxxx
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx 
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: http://groups.yahoo.com/group/amibroker/files/groupfaq.html



Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.