May we collect analytics to improve ReelAtlas? We collect page views, clicks, scrolling, active time and page performance. In 10% of eligible mouse sessions, positions are grouped into aggregate cells. We do not record sessions, field contents, search text or IP addresses. You can change your choice at any time.

How our analytics works

Lab

Spread lab

Two distributions, the same mean and different individual outcomes.

Compare two distributions with visible parameters and observe their means and spread. Each outcome belongs to a model whose parameters are shown. The exercise does not measure the behaviour of a specific slot game.

A large number of observations leaves the probabilities of an individual independent draw unchanged. A previous streak does not mean the next outcome must restore the balance. The model is for understanding spread and cannot select a stake or predict a session.

Variability model

The model uses hypothetical units to show mathematical relationships. It cannot predict the outcome of any game.

How the model works

Standard deviation measures how spread out the model outcomes are around the mean. Two models with the same mean can have different spreads.

Each distribution has two outcomes, the specified value and zero. When the means are equal, the model calculates the positive outcome for distribution B automatically. Change the probabilities to compare the spread.

Distribution A
Probability distribution: 0: 75 %; 3: 25 %
Theoretical mean per trial
0,75
Variance (units²)
1,688
Standard deviation
1,299
Distribution B
Probability distribution: 0: 50 %; 1,5: 50 %
Theoretical mean per trial
0,75
Variance (units²)
0,563
Standard deviation
0,75

Sources

  1. NIST: gallery of probability distributionsChecked