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

Re: [amibroker] "Random prices" (was Re: Backtest using equity curve)



PureBytes Links

Trading Reference Links




It is even then not true. Do you really believe that for
example the price in the range 24 to 26 of the below
said stock is random? That is: will the price be jumping
randomly in that area? No, Sir. The price will be "build" and
it will "move" but not randomly jump. As said: prices are 
driven only by supply and demand, and not by any random 
event. Since you seem to believe in randomness in stock 
prices:  to what degree (%) do you think are price moves random?
 
<BLOCKQUOTE 
>
  ----- Original Message ----- 
  <DIV 
  >From: 
  wavemechanic 
  
  To: <A title=amibroker@xxxxxxxxxxxxxxx 
  href="">amibroker@xxxxxxxxxxxxxxx 
  Sent: Monday, November 17, 2003 5:40 
  PM
  Subject: Re: [amibroker] "Random prices" 
  (was Re: Backtest using equity curve)
  
   
  ----- Original Message ----- 
  From: <<A 
  href=""><FONT 
  size=2>uenal.mutlu@xxxxxxxxxxx<FONT 
  size=2>>
  To: <<A 
  href=""><FONT 
  size=2>amibroker@xxxxxxxxxxxxxxx<FONT 
  size=2>>
  Sent: Monday, November 17, 2003 10:46 
  AM
  Subject: Re: [amibroker] "Random prices" (was Re: 
  Backtest using equity curve)
  
  > I naturally disagree :-)> So, you and 
  quanttrader are really saying that> the stock prices are indeed really 
  random?!> So, then why use T/A or AB at all?> Why on hell would 
  anybody invest in random things (except in lotto etc.)?
   
  I don't think anyone is 
  saying that a price series is completely random, but rather that a random 
  series can look like a price series.  Any price series is produced 
  by contributions from three sources: trending, cyclical, and 
  random.
  <FONT 
  size=2>> > Ok, here is a practical example: imagine a stock> 
  closed at 25 yesterday. Do you really believe that> the intraday price 
  of this stock today will make> random moves between 0 and say 50 
  ?> Intraday it will move around 25, but will definitely not 
  make> fe. something like the following: 25, 1, 50, 25, 10, 40, 0, 1, 
  50> If this practically is not possible with this stock then> it 
  definitely is not random. IMHO a basic fact.> > > 
  > ----- Original Message -----> From: "Tomasz Janeczko" 
  <<FONT 
  size=2>amibroker@xxxxxx>> 
  To: <<A 
  href=""><FONT 
  size=2>amibroker@xxxxxxxxxxxxxxx<FONT 
  size=2>>> Sent: Monday, November 17, 2003 3:49 PM> Subject: 
  Re: [amibroker] "Random prices" (was Re: Backtest using equity curve)> 
  > > > Uenal,> >> > I fully agree with 
  quanttrader.> >> > Even code you supplied can be modified 
  to produce chart that is random too> > but looks much closer to 
  'real' prices.> >> > Graph = 100+ Cum( -1 + Random() * 2.0 
  );> >> > Plot(Graph, "Random graph", colorBlue);> 
  >> > Best regards,> > Tomasz Janeczko> > 
  amibroker.com> >> > Best regards,> > Tomasz 
  Janeczko> > amibroker.com> > ----- Original Message 
  -----> > From: "quanttrader714" <<A 
  href=""><FONT 
  size=2>quanttrader714@xxxxxxxxx<FONT 
  size=2>>> > To: <<A 
  href=""><FONT 
  size=2>amibroker@xxxxxxxxxxxxxxx<FONT 
  size=2>>> > Sent: Monday, November 17, 2003 3:39 PM> > 
  Subject: [amibroker] "Random prices" (was Re: Backtest using equity 
  curve)> >> >> > This proves nothing.  Your 
  model is flawed.  Generate a chart with one> > dimensional 
  Brownian motion and there's not a person on this board who> > would 
  be able to tell it from a "real" price chart.  An omniscient> > 
  being could create perfect deterministic models of the markets but for> 
  > mere mortals, there's significant randomness caused by an 
  incredibly> > complex mix of competing forces that "nudge" prices in 
  different> > directions, from institutional purchases to Johnny 
  Jones cashing in to> > pay for his daughter's wedding to daytraders, 
  etc., etc., etc.> > Certain forces will prevail and/or be in synch 
  to varying degrees over> > time.  But even in a totally random 
  process, anything that can happen,> > will happen if you wait long 
  enough.> >> >> > --- In <A 
  href=""><FONT 
  size=2>amibroker@xxxxxxxxxxxxxxx, 
  <FONT 
  size=2>uenal.mutlu@x... 
  wrote:> > > // generate random series in the range 0 to 100 and 
  plot it> > > Graph = Random() * 100;> > > 
  Plot(Graph, "Random graph", colorBlue);> > >> > > 
  Does any real chart look like such a random chart: NO.> > > This 
  proves the basic fact that nothing in the markets> > > is or was 
  ever random.> > > UM> > >> > >> 
  > >> > > ----- Original Message -----> > > 
  From: "palsanand" <<A 
  href=""><FONT 
  size=2>palsanand@x...>> 
  > > To: <<A 
  href=""><FONT 
  size=2>amibroker@xxxxxxxxxxxxxxx<FONT 
  size=2>>> > > Sent: Monday, November 17, 2003 1:19 AM> 
  > > Subject: [amibroker] Re: Backtest using equity curve> > 
  >> > >> > > In his book "The Profit Magic of 
  Stock Transaction Timing", J.M.> > > Hurst proves that market 
  movement is not random, and by analyzing a> > > large "stable" of 
  underlying instruments one could find excellent> > > 
  opportunities for profit each and every day.  The movement is not> 
  > > random but non-stationary because markets do not move without 
  a> > > purpose or a goal, they move because of an imbalance 
  between supply> > > (sellers) and demand (buyers) with the price 
  tending to equalize it.> > > However the outcomes are random, 
  i.e, unknown and the probability of> > > winning is undetermined, 
  i.e., not a constant.> > >> > > Identifying 
  persistent price patterns helps one to determine the> > > 
  dependance of the outcomes.  The existence of a pullback or a 
  rally> > > situation is dependant on the existance of a previous 
  uptrend or a> > > downtrend and so is the existance of a trend 
  reversal.  What's real> > > price movement in response to a 
  clear signal and what's just random> > > noise? Figuring out the 
  difference is vital and according to John F.> > > Ehlers in a 
  recent article in S & C Magazine such a distinction can> > > 
  be important to trading. If one could avoid periods when the market> 
  > > has no clear trend (just enjoy being flat), one could avoid 
  whipsaws> > > and get cleaner trades. If one could identify 
  periods that were> > > filled with noise and no clear signals in 
  either direction, one> > could> > > also switch trading 
  tactics to suit the situation, for e.g., day-> > > trading 
  instead of position-trading. At the very least, one would> > > 
  know what situation one faces.> > >> > > rgds, 
  Pal> > > --- In <A 
  href=""><FONT 
  size=2>amibroker@xxxxxxxxxxxxxxx, 
  "quanttrader714"> > > <<A 
  href=""><FONT 
  size=2>quanttrader714@x...> 
  wrote:> > > > You guys are confusing randomness, independence 
  and stationarity> > > big time.> > > >> 
  > > > --- In <A 
  href=""><FONT 
  size=2>amibroker@xxxxxxxxxxxxxxx, 
  "Dave Merrill" <<FONT 
  size=2>dmerrill@x...>> > 
  > wrote:> > > > > agreed. if the fact that a trading 
  system did well in the past> > > has no> > > > 
  > bearing whatsoever on whether it does well in the future, how> 
  > can> > > we> > > > know> > > 
  > > anything at all about the future performance of a proposed> 
  > trading> > > > system?> > > > 
  >> > > > > dave> > > > >> > 
  > > >   The gambler¡Çs fallacy is a fallacy because the 
  gambler> > ignores> > > the> > > > > 
  independence of the outcomes and looks for patterns that do not> > 
  > > exist.  If> > > > > we have designed trading 
  systems based on recognition of> > patterns> > > 
  that> > > > > precede profitable trading opportunities, and 
  if those patterns> > > are> > > > > 
  persistent, then we no longer have random, independent outcomes.> > 
  > Our> > > > > trading systems do have serial 
  dependencies and upward sloping> > > equity> > > 
  > > curves.  So analysis of the equity curve provides an 
  indication> > > of the> > > > > health of the 
  trading system.> > > > >> > > > 
  >> > > > >> > > > >   
  Howard






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.