Skip to content
GetProfitable
Search
Dictionary

Signal-to-noise ratio

How large a real effect is relative to the random variation around it; in financial returns it is usually tiny.

Daily equity index returns have a standard deviation around 1%. A very good long-run edge might be 0.03% a day. That is a signal-to-noise ratio of about 1 to 33 on a single day, which is why a month of results tells you almost nothing.

The consequence is sample size. To detect a 0.03% daily edge with any confidence you need thousands of observations, and markets only produce about 252 trading days a year. This is the single most underappreciated fact in strategy research.

It also explains why plots deceive. An equity curve is a cumulative sum, and cumulative sums of noise look like trends. Always look at the distribution of individual returns alongside the curve.

Related: sample-size

See it drawn

Original diagrams for the ideas on this page. Illustrative, not real market data.

The spread of outcomes behind an expectancyA histogram of forty trades: a tall block of small losses on the left, a low spread of larger wins on the right, and a line marking the average outcome.NUMBER OF TRADES051024 LOSSES, AVG −$20016 WINS, AVG +$600EXPECTANCY +$120−$400−$200$0+$200+$400+$600+$800PROFIT OR LOSS PER TRADEexpectancy = (40% × $600) − (60% × $200) = +$120 per trade
Expectancy: the average trade. Forty trades sorted by outcome: 24 small losses and 16 larger wins. Weighting each side by how often it happens gives the average result per trade, marked here by the dashed line at +$120.

Educational only, not advice. Spotted an error? Post in Site Feedback.