Skip to content
Sports.co

Advanced

Expected value, variance, and sample size

The arithmetic of long-run outcomes, and why short samples are close to uninformative.

Last ReviewedFirst-party educational text
Illustration — no market data

AI summary

No summary is published for this page. When summaries are enabled they will restate only what this page already publishes — the lesson body on this page, reduced to key takeaways. — and each one will carry the model name and the time it was generated.

Status: reserved · no generated text on this page

How this lesson runs

  1. 01

    The calculation

  2. 02

    Sample size

  3. 03

    Model humility

Want this applied to a specific price? The Sports.co Analyst walks through the arithmetic. It explains method only — never picks.

Video walkthrough: Expected value, variance, and sample size

No verified video is linked here yet. This slot fills only with official or first-party footage we can attribute on screen.

Reserved for first-party or officially licensed footage. Attribution appears on screen before anything plays here.

The calculation

Expected value is the probability-weighted outcome minus cost. If your probability estimate is 55% against a price implying 52%, the difference is the estimated edge — before fees, and only as good as the estimate itself.

Sample size

With a small theoretical edge, a large number of observations is needed before results can be distinguished from noise. Short-run results are dominated by variance.

Model humility

Estimated probabilities carry error. Treating a point estimate as certain is the most common analytical failure in this area — which is also why this site publishes no confidence scores it cannot substantiate.

Sources

No source is connected to this section yet. Nothing here should be read as a current factual claim.

Method explained in our own words. This lesson asserts no market price, result, or statistic.