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

RE: [amibroker] On Robustness, Post #1



PureBytes Links

Trading Reference Links




Thanks 
for the post MF2!
<FONT face=Arial color=#0000ff 
size=2> 
<FONT 
size=2>Given Steve's example of the CMO5 which I assume is coded to detect the 
cross of the indicator thru a value, how would you determine that value for 
your intial testing?  This is the case below where you say "<FONT 
face="Courier New" color=#000000>Test *unoptimized* system on small, mid & 
large cap stocks in bull, bear & sideways market conditions, same parameters 
for all"
<FONT face="Courier New" 
size=2> 
<FONT face=Arial color=#0000ff 
size=2>Thanks!
<FONT face=Arial color=#0000ff 
size=2> 
<FONT face=Arial color=#0000ff 
size=2>d

  
  <FONT 
  face=Tahoma size=2>-----Original Message-----From: MarkF2 
  [mailto:feierstein@xxxxxxxxx] Sent: Saturday, November 01, 2003 
  2:50 PMTo: amibroker@xxxxxxxxxxxxxxxSubject: [amibroker] 
  On Robustness, Post #1This is in response to DT's and 
  others' requests to provide moredetails on my 9 robustness 
  criteria.First some administrative anouncements, lol.  I've 
  decided to provide them one-by-one, first due to my time constraints, 
  second because I feel that's the best way to discuss them and third 
  because I want to see how this goes.  I welcome all constructive 
  debate, especially opposing views supported by quantitative 
  analysis.  But if this degenerates into a flame war, I've got better 
  things to do with my time.  Treat me with respect and I'll treat you 
  with respect.  There seems to be a lot of interest in this topic, so 
  let's please have a collegial and productive discussion.  This is 
  post 1 of 9 (notcounting the dialog inbetween, let's see how far we can 
  get :-).Why care about robustness?  For whatever reasons, markets 
  change.  We could spin our wheels forever discussing time series 
  theory, serial dependencies, random walk, nonstationarity, etc., like 
  academiciansdo and get nowhere (as they do), or we can try to cut through 
  the crapand deal with it (the simple fact that markets constantly change). 
  My weapon of choice is robustness.  You could say I have a robustness 
  obsession and my criteria are overkill.  But that's my choice and 
  you're free to make your own on how far you want to take this, if at 
  all.OK, I lied.  There will be some, very light discussion of 
  statistics because some criteria are steeped in statistical theory.  
  But mostcan be reduced to simple, mechanical procedures that can be 
  graphed ina spreadsheet and visually and intuitively interpreted.  
  Othersrequire simulation software and one requires proprietary software 
  butwe'll cross that bridge when we come to it.  Speaking of 
  proprietary, there are some things I simply won'tdisclose, such as 
  specific parameters for certain criteria.  So pleaserespect my wishes 
  and don't ask.  I have my reasons.  So evaluate thison your own 
  and decide for yourself what place, if any, the criteriahave in your 
  trading.  They work great for me but I make no claim thatthey're the 
  Holy Grail of robustness and am sure that some of you willcome up with 
  better ideas if there's enough interest and discussion.  With 
  that long winded intro, here's Criterion #1:Test *unoptimized* system 
  on small, mid & large cap stocks in bull, bear & sideways market 
  conditions, same parameters for all.  I usethe stocks of the S&P 
  600, 400, and 500 indices and 2 year bull, bearand sideways periods (for a 
  total of 6 years per stock).  Rationalebehind this: to find systems 
  that profitably *tested out in the past*on a large number of (somewhat 
  tradeable) stocks of varying marketcaps in multiple sectors under 
  different market conditions, under the assumption that this indicates the 
  system is robust enough toprofitably *trade select issues in the 
  future*.  More on robust issue selection in later criteria. Looking 
  for net profitability on all mkt cap and mkt condition subtests, and 
  profitable on the majority (>50%) of issues in each subtest, the more 
  the better.  Sometimes I cuta system some slack if it's close on one 
  or two subtests, it's a judgement call.  My commission setting(s) in 
  AB: proprietary, basedon my *slippage* research using data from actual 
  trades.  But youcould choose an arbitrary say, 1% to get 
  started.  Date settings formy 2 year intervals: proprietary but you 
  can easily find your own by eyeballing a chart of a major index.  
  Just use the same ones eachtime so you compare apples to 
  apples.   My lite version of this is 2year bull and bear periods 
  on the ND100 and SP100 stocks, which Isometimes run as a quick pre-screen. 
  Next time someone posts a system,run it through the lite or full 
  version.  Or test the systems in theAFL library.  The more 
  systems you run through, the more intuitive ofa feel for robustness you'll 
  get.  Note that I'm *not* saying you shouldn't or can't successfully 
  trade something that doesn't meetthis standard, lol.  That's 
  obviously not true!  I was asked toexplain my robustness criteria and 
  that's what I'm doing.  Period. This criterion is a post-Amibroker 
  creation, BTW.  Pre-Amibroker I hada small test portfolio of diverse 
  issues I used instead and it did adecent job. I run this now because I now 
  (easily) can, *many* thanksto Tomasz.  If you're thinking, geez, why 
  bother with this, askyourself a simple question. *All else being equal*, 
  would you feelmore confident trading (with your money) a system that 
  passes thistest or one that fails it? 
  Regards,MarkSend 
  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. 







Yahoo! Groups Sponsor












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.