StatsCalculators.com

Law of Large Numbers Simulation

Simulations

Coin Flip Simulation

Parameters

Current Probability:0.00%
Expected Probability:50.00%

Results

Understanding the Results

  • The blue line shows the probability of getting heads as trials increase
  • The red dashed line shows the theoretical probability (50%)
  • Notice how the experimental probability converges to 50% over time
  • This demonstrates the Law of Large Numbers in action

Dice Roll Simulation

Parameters

Current Average:0.00
Expected Average:3.50

Results

Understanding the Results

  • The blue line shows the average dice roll value over time
  • The red dashed line shows the expected average (3.5)
  • Notice how the experimental average converges to 3.5 as trials increase
  • This demonstrates how sample means converge to the true population mean

Card Draw Simulation

Parameters

Current Probability:0.00%
Expected Probability:7.69%

Results

Understanding the Results

  • The blue line shows the probability of drawing an ace over time
  • The red dashed line shows the theoretical probability (4/52 ≈ 7.69%)
  • Notice how the experimental probability converges to 7.69% as trials increase
  • This demonstrates the Law of Large Numbers for a less intuitive probability

Learn More

What is the Law of Large Numbers?

The Law of Large Numbers is a fundamental principle in probability theory and statistics that describes how the average of results obtained from repeating an experiment many times will converge to the expected value. Think of it as nature's way of revealing its true probabilities through repeated observations.

"As the number of trials increases, the experimental probability approaches the theoretical probability."

Mathematical Foundation

Consider a sequence of independent and identical trials X1,X2,...,XnX_1, X_2, ..., X_n with expected value μ\mu. The sample average is:

Xˉn=1ni=1nXi\bar{X}_n = \frac{1}{n}\sum_{i=1}^n X_i

As the number of trials (nn) approaches infinity:

P(Xˉnμ<ϵ)1P(|\bar{X}_n - \mu| < \epsilon) \to 1

This means the probability that our sample average differs from the true mean by any small amount (ϵ\epsilon) approaches zero as we increase our sample size.