NexusFi: Find Your Edge


Home Menu

 





Is this a valid approach from a statistical standpoint?


Discussion in Psychology and Money Management

Updated
      Top Posters
    1. looks_one TraderTed with 2 posts (0 thanks)
    2. looks_two vvhg with 2 posts (1 thanks)
    3. looks_3 Quick Summary with 1 posts (0 thanks)
    4. looks_4 geott with 1 posts (1 thanks)
      Best Posters
    1. looks_one ThatManFromTexas with 2 thanks per post
    2. looks_two geott with 1 thanks per post
    3. looks_3 imPairsonator with 1 thanks per post
    4. looks_4 vvhg with 0.5 thanks per post
    1. trending_up 3,263 views
    2. thumb_up 5 thanks given
    3. group 7 followers
    1. forum 12 posts
    2. attach_file 2 attachments




 
Search this Thread

Is this a valid approach from a statistical standpoint?

  #1 (permalink)
 TraderTed 
Hamburg + Germany
 
Experience: Intermediate
Platform: Motive Wave, Oanda
Posts: 18 since Mar 2010
Thanks Given: 13
Thanks Received: 15

Hi everyone,

I have a question concerning a trading rule, which I have come across from 2 different Gurus. The one explained it directly the other had it somehow hidden in his rules.

Here it is in my words:

Letīs assume we have a trading strategy that is basically 80% winning, but the outcome is more or less breakeven.
So the 20% loosers eat up all the winners.

Now the rule is to stop trading when 3 winners came in a row. Because - they say - after 3 winners in a row the probability of encountering a looser gets too high. Now you either stop trading for the day, or at least till the next looser passed by untaken.

Is this a valid approach to skip the low probability loosers, and transform a breakeven strategy to a winning strategy?

As far as I understand statistics it is not possible to know, where the winners ( or loosers) come in.

But is it possible to have a probabilty of a series of winners in a row? Like 3 or 4 winners in a row, with a basic 80% winning strategy for example??

Started this thread Reply With Quote

Can you help answer these questions
from other members on NexusFi?
NexusFi Journal Challenge - April 2024
Feedback and Announcements
ZombieSqueeze
Platforms and Indicators
Request for MACD with option to use different MAs for fa …
NinjaTrader
My NT8 Volume Profile Split by Asian/Euro/Open
NinjaTrader
 
Best Threads (Most Thanked)
in the last 7 days on NexusFi
Retail Trading As An Industry
58 thanks
Battlestations: Show us your trading desks!
52 thanks
NexusFi site changelog and issues/problem reporting
48 thanks
What percentage per day is possible? [Poll]
31 thanks
GFIs1 1 DAX trade per day journal
31 thanks

  #3 (permalink)
 
liquidcci's Avatar
 liquidcci 
Austin, TX
 
Experience: Master
Platform: ninjatrader, r-trader
Trading: NQ, CL
Posts: 866 since Jun 2011
Thanks Given: 610
Thanks Received: 1,091



TraderTed View Post
Hi everyone,

I have a question concerning a trading rule, which I have come across from 2 different Gurus. The one explained it directly the other had it somehow hidden in his rules.

Here it is in my words:

Letīs assume we have a trading strategy that is basically 80% winning, but the outcome is more or less breakeven.
So the 20% loosers eat up all the winners.

Now the rule is to stop trading when 3 winners came in a row. Because - they say - after 3 winners in a row the probability of encountering a looser gets too high. Now you either stop trading for the day, or at least till the next looser passed by untaken.

Is this a valid approach to skip the low probability loosers, and transform a breakeven strategy to a winning strategy?

As far as I understand statistics it is not possible to know, where the winners ( or loosers) come in.

But is it possible to have a probabilty of a series of winners in a row? Like 3 or 4 winners in a row, with a basic 80% winning strategy for example??


You have to keep stats on everything and see how things are affected. But from my experience using a method like that does not work. Probabilities are extremely important but there is just no way to determine whether next trade will be a winner or loser based on previous 3 trades. On a surface level when I look at my stats I think something like that would work but when I put it through extensive testing it does not. It just does not stand the test of time over many trades.

"The day I became a winning trader was the day it became boring. Daily losses no longer bother me and daily wins no longer excited me. Took years of pain and busting a few accounts before finally got my mind right. I survived the darkness within and now just chillax and let my black box do the work."
Reply With Quote
  #4 (permalink)
 imPairsonator 
Thessaloniki, Greece
 
Experience: Beginner
Platform: QTS
Broker: IB
Trading: Equities, NQ
Posts: 166 since May 2012
Thanks Given: 104
Thanks Received: 395

It's not impossible if there is some sort of relationship between the result of sequential trades. Usually this works the other way around though, i.e. several losing trades may indicate a change in market regime into an unfavorable environment for a particular strategy. Not sure what the rationale would be for not trading after several winners.

In any case, you'd have to establish such a relationship robustly by analyzing a long sample of trade results.

Follow me on Twitter Reply With Quote
The following user says Thank You to imPairsonator for this post:
  #5 (permalink)
 geott 
France
 
Experience: Advanced
Platform: MT4/NT
Trading: YM, DAX, Fx, CFD
Posts: 25 since Oct 2010
Thanks Given: 18
Thanks Received: 40


TraderTed View Post
Hi everyone,


But is it possible to have a probabilty of a series of winners in a row? Like 3 or 4 winners in a row, with a basic 80% winning strategy for example??


1 = 80 %
2 = 0.8 ^2 = 64%
3 = 0.8 ^3 = 51.2%
4 = 0.8 ^4 = 40.96%

Reply With Quote
The following user says Thank You to geott for this post:
  #6 (permalink)
 
vvhg's Avatar
 vvhg 
Northern Germany
 
Experience: Intermediate
Platform: NT
Trading: FDAX, CL
Posts: 1,583 since Mar 2011
Thanks Given: 1,016
Thanks Received: 2,824


geott View Post
1 = 80 %
2 = 0.8 ^2 = 64%
3 = 0.8 ^3 = 51.2%
4 = 0.8 ^4 = 40.96%

But only if the single trades are completely uncorrelated. In which case the approach of skipping a trade would not work as the chance that the next trade will be a winner would always be 80% regardless of the outcome of previous trades.
However, if the trades were correlated in some way or another, which they probably arent (to any significant degree) the approach could work (or perhaps the opposite approach).
The only way to find out is to keep extensive trade records, kind of like train spotting, only more compulsive

Vvhg

Hic Rhodos, hic salta.
Reply With Quote
The following user says Thank You to vvhg for this post:
  #7 (permalink)
 
MWinfrey's Avatar
 MWinfrey 
Lubbock TX
 
Experience: Intermediate
Platform: NinjaTrader
Broker: Stage 5 Trading
Trading: CL
Posts: 1,878 since Jul 2009
Thanks Given: 1,450
Thanks Received: 3,335

Another thread talks about this which is the "Gambler's Fallacy". I'm providing the link to the first post in the thread but it very quickly gets into what you are talking about.


Reply With Quote
  #8 (permalink)
 
ThatManFromTexas's Avatar
 ThatManFromTexas 
Houston,Tx
 
Experience: Advanced
Platform: NinjaTrader
Broker: Mirus Futures/Zen-Fire
Trading: TF
Posts: 2,265 since Feb 2010
Thanks Given: 1,206
Thanks Received: 4,348


TraderTed View Post
Hi everyone,

I have a question concerning a trading rule, which I have come across from 2 different Gurus. The one explained it directly the other had it somehow hidden in his rules.

Here it is in my words:

Letīs assume we have a trading strategy that is basically 80% winning, but the outcome is more or less breakeven.
So the 20% loosers eat up all the winners.

Now the rule is to stop trading when 3 winners came in a row. Because - they say - after 3 winners in a row the probability of encountering a looser gets too high. Now you either stop trading for the day, or at least till the next looser passed by untaken.

Is this a valid approach to skip the low probability loosers, and transform a breakeven strategy to a winning strategy?

As far as I understand statistics it is not possible to know, where the winners ( or loosers) come in.

But is it possible to have a probabilty of a series of winners in a row? Like 3 or 4 winners in a row, with a basic 80% winning strategy for example??


@TraderTed


There are just too many unknown variables that can affect the outcome...

If a system is a trend following system , the trading day is a strong trending day ... and the market is in sync with your system ... you can have all winning trades ... unfortunately, you will hate yourself because you stopped trading after the first three winning trades

The same system on a very choppy or range bound day could produce all losers ... unfortunately you will hate yourself for continuing to take trades waiting for the 80% wins to kick in

Some days the market showers you with gold ...





Some days it just gives you "Golden Showers" ....


I'm just a simple man trading a simple plan.

My daddy always said, "Every day above ground is a good day!"
Reply With Quote
The following 2 users say Thank You to ThatManFromTexas for this post:
  #9 (permalink)
 TraderTed 
Hamburg + Germany
 
Experience: Intermediate
Platform: Motive Wave, Oanda
Posts: 18 since Mar 2010
Thanks Given: 13
Thanks Received: 15


geott View Post
1 = 80 %
2 = 0.8 ^2 = 64%
3 = 0.8 ^3 = 51.2%
4 = 0.8 ^4 = 40.96%

Thanks for all the answers so far.

Geott : I was looking for just this numbers!

But I did not get completely what VVHG said.

Do the trades have to be uncorrelated or correlated for this "series probabilities" to work?

In which case would I fall for the "gamblers fallacy"?

Is this right?:

Correlated:
1 = 80 %
2 = 0.8 ^2 = 64%
3 = 0.8 ^3 = 51.2%
4 = 0.8 ^4 = 40.96%

and

Uncorrelated:
1= 80%
2=80%
3=80%
4=80%


or the other way round ?

Started this thread Reply With Quote
  #10 (permalink)
 
vvhg's Avatar
 vvhg 
Northern Germany
 
Experience: Intermediate
Platform: NT
Trading: FDAX, CL
Posts: 1,583 since Mar 2011
Thanks Given: 1,016
Thanks Received: 2,824



TraderTed View Post
Thanks for all the answers so far.

Geott : I was looking for just this numbers!

But I did not get completely what VVHG said.

Do the trades have to be uncorrelated or correlated for this "series probabilities" to work?

In which case would I fall for the "gamblers fallacy"?

Is this right?:

Correlated:
1 = 80 %
2 = 0.8 ^2 = 64%
3 = 0.8 ^3 = 51.2%
4 = 0.8 ^4 = 40.96%

and

Uncorrelated:
1= 80%
2=80%
3=80%
4=80%


or the other way round ?

It is connected to the gamblers fallacy. Talking about uncorrelated trades the chance is always 80% (in this example) for each INDIVIDUAL trade seen as a single, uncorrelated event (which it is). The chance for four winners in a row would be 4 = 0.8 ^4 = 40.96%. BUT the fourth trade of this series (regardless of the outcome of the previous 3) always has a 80% chance.
So if you skip trades in a system where the trades are uncorrelated or insignificantly correlated, you gain nothing, other than experiencing the gamblers fallacy first hand

vvhg

Hic Rhodos, hic salta.
Reply With Quote





Last Updated on May 22, 2012


© 2024 NexusFi™, s.a., All Rights Reserved.
Av Ricardo J. Alfaro, Century Tower, Panama City, Panama, Ph: +507 833-9432 (Panama and Intl), +1 888-312-3001 (USA and Canada)
All information is for educational use only and is not investment advice. There is a substantial risk of loss in trading commodity futures, stocks, options and foreign exchange products. Past performance is not indicative of future results.
About Us - Contact Us - Site Rules, Acceptable Use, and Terms and Conditions - Privacy Policy - Downloads - Top
no new posts