1999issue C041-7
Pre-trade size filters for expectancy and ruin
The historical workflow treated size as a success filter before the first unit. Expected value, a cap on how much equity one idea may consume, and survival through a losing streak were the checks that decided whether a size was viable.
- Expected value equals win probability times average win minus loss probability times average loss, so a high win rate is not enough if the typical loss is large relative to the typical win.
- Position size is a success filter that is often skipped when equity is too small for the vehicle, stop distance, and exposure.
- Risk on an open position is the amount that would actually be lost at the planned exit, so a fixed dollar stop is not a substitute for sizing off equity.
- If the current size cannot absorb four or five losses in a short sample, ten in a row, or even twenty at low reliability, that size is not viable.
What the historical workflow required
Before entry, a stop-loss point that protects capital and a decision on how much equity one idea may consume are both required. The stop-loss-point is the pre-planned exit that defines how much capital one open position is allowed to lose. The initial-risk-unit is the planned loss if the first stop is hit; later outcomes are counted as multiples of that unit.
Modeled successful traders shared low-risk ideas, position sizing, and discipline more than they shared a common entry method.
Expected value as the first reject
Expected value equals win probability times average win minus loss probability times average loss. That figure is the long-run average result per unit risked.
An 80 percent win of 1 against a 20 percent loss of 10 yields about minus 1.20 per unit risked. Reversing those magnitudes yields about plus 1.20. A high win rate does not make a process valuable if the typical loss is large relative to the typical win.
A cap on how much equity one idea may consume
Position size is a success filter that is often skipped when equity is too small for the vehicle, stop distance, and exposure. A position-concentration-limit is a pre-entry cap on how much account equity one idea may consume, set from stop distance, volatility, and exposure so a single loss cannot dominate the book.
Viable starting equity is vehicle-specific. One discussion treated 50000 as too little for index-futures day trading, while 10000 could suffice in a quieter agricultural contract.
Risk on an open position is the amount that would actually be lost at the planned exit, so a fixed dollar stop is not a substitute for sizing off equity.
A size that cannot survive a losing streak
Risk of ruin is the chance that a run of losses, given current size, stop distance, and equity, will wipe the account or force it out of the game. If a process cannot absorb a long losing streak, four or five losses in a short sample, ten in a row, or even twenty at low reliability, the current size is not viable.
A positive-expectancy sequence of 60 percent 1-unit wins and 40 percent 1-unit losses still left only 2 of 40 players ahead after 100 size decisions.
All readings on this track · 15 readings
- 1991Keep one risk ceiling after equity highs
- 1999Pre-trade size filters for expectancy and ruin
- 2000Budget the loss before entry with stops and position limits
- 2002Retest the entry before you exit
- 2002Option income after volatility and capital gates
- 2002Cap, scale, and delever when research buys late
- 2003Staying power starts as a planned-loser sizing rule
- 2006Leverage caps and concentration limits
- 2007A first-trade survival sequence for leveraged futures
- 2010Bound trend risk before the trade is placed
- 2011Event shocks, size caps, and second-order reweights
- 2014A copied scale-in ladder is not a personal risk plan
- 2018Worst-day caps for clustered system books
- 2019Pair-spread layer limits and event shocks
- 2020Pretrade quantity filters that bound account risk