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

RE: [amibroker] Re: Good & Bad Re-Optimizations (for Dave)



PureBytes Links

Trading Reference Links




<FONT face=Arial color=#0000ff 
size=2>Dave,
<FONT face=Arial color=#0000ff 
size=2> 
You 
remind me a lot of myself in that you seem to be more focused on writing code to 
find your trading system rather than backing off and looking at the big 
picture. Take a look at Steve Karnish's last post.  Then go back in 
the archives and read some more on the CMO system he has posted on this 
forum.  Take some of these ideas and put them in a simple backtest and run 
them - also, construct some idicators around the basic cmo and other things and 
look at it visually.  Forget about the self optimizing stuff for awhile 
until you can "see" the effects of changes in the params in the indicator 
code.  
<FONT face=Arial color=#0000ff 
size=2> 
And as 
a wise muse once told me - KEEP IT SIMPLE 
<FONT face=Arial color=#0000ff 
size=2> 
<FONT face=Arial color=#0000ff 
size=2>d

  
  <FONT 
  face=Tahoma size=2>-----Original Message-----From: Dave Merrill 
  [mailto:dmerrill@xxxxxxx] Sent: Thursday, October 30, 2003 11:39 
  AMTo: amibroker@xxxxxxxxxxxxxxxSubject: RE: [amibroker] 
  Re: Good & Bad Re-Optimizations (for Dave)
   
  <BLOCKQUOTE 
  >
    Not mechanical enough ?  I'm clearly a believer in the use of 
    mechanical systems but I wouldn't go so far as to say that the 
    design, building, testing and evaluation of a system needs to result 
    in an automated club that beats me over the head.  <SPAN 
    class=385213116-30102003><FONT color=#0000ff 
    size=2> 
  <SPAN 
  class=385213116-30102003>me neither. I just 
  want to feel like I understood how to evaluate systems well enough to make a 
  set of real principles out of it. it's always our choice what to actually 
  do.
  <SPAN 
  class=385213116-30102003> 
  <BLOCKQUOTE 
  >
    Unpredictably changing data ... hmmmm ... doesn't that warrant 
    having parameters for systems that aren't near cliffs on surface plots 
    ?<FONT color=#0000ff 
    size=2> 
  <SPAN 
  class=385213116-30102003>sure, but aren't the cliffs we're really concerned 
  with cliffs in price behavior, not parameter values? parameters don't change 
  by themselves, data does.
  <SPAN 
  class=385213116-30102003> 
  is 
  there a necessary link between EMAs 20 through 30 all working reasonably well, 
  and EMA 25 being more robust than EMA 30 against data variations? is that 
  so obviously true that I shouldn't even be asking?
  <SPAN 
  class=385213116-30102003> 
  <SPAN 
  class=385213116-30102003>daveSend 
  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.