Sample size
How many observations a statistic is built on.
A win rate of 100 percent sounds decisive until you learn it rests on two cases. The number of observations governs how much weight a figure can carry, and it is the first thing to look for.
Small samples do not merely make a result uncertain, they make striking results more likely. With few observations, extreme averages appear easily by chance, which is exactly why the most spectacular numbers tend to rest on the fewest cases.
The usual mistake. Be especially wary when the sample size is not stated at all. A published win rate with no observation count behind it cannot be assessed, and usually would not survive being assessed.
See also
This definition is part of the EPTA5 lexicon, written so that a reader who does not work in finance can follow our market notes without stopping. It is general information and not investment advice. Read the notes.