Sample size

The number of independent observations a conclusion rests on.

Example

Five of six is 83.33%. One different outcome would make it 100.00% or 66.67% - the same kind of headline share, resting on nothing.

Important

A percentage carries no trace of how many observations produced it, and that is what makes a thin one persuasive: 83% looks identical whether it rests on six cases or six hundred. Write the count beside every share, including your own.

Related terms

• Base rate — How often an outcome occurs across the whole population of similar cases, before you know anything specific about the one in front of you.
• Variance — How widely actual outcomes spread around their average. High variance means individual results routinely land far from the expected value, in both directions.
• Calibration — How closely the likelihoods you state match how often those things actually happen, measured across many stated likelihoods rather than any one of them.

Lessons that explain it

• One cheque is not this asset class; twenty of them might be — The economics in this subject describe a portfolio of many small bets, not a single concentrated one - and somebody who can only make two or three checks is not really practising this asset class in any statistical sense, whatever it feels like while they are doing it. (9 min)
• Reading an old entry without rewriting it — The entry is only half the practice. The other half is going back to it later and reading what you actually wrote, rather than what you now wish you had. (11 min)

All 578 terms in the Investing glossary