Course contentsShow
← Data Science
Lesson 125 of 2,1454. Discrete Probability DistributionsFree lesson

Bernoulli Mean and Variance

Derive that E(X)=p and Var(X)=p(1-p) for a Bernoulli random variable and interpret these values.

Bernoulli Mean and Variance

What you'll learn: You'll discover the formulas for the expected value and variance of a Bernoulli random variable and understand what they tell you about coin-flip-like experiments.

Understanding the Formulas

You already know that a Bernoulli random variable X represents a single trial with two outcomes: success (X=1) with probability p, or failure (X=0) with probability 1-p.

Now let's find the expected value (mean):

E(X) = 0·(1-p) + 1·p = p

That's it! The expected value of a Bernoulli trial equals the probability of success. If you flip a coin with p=0.7 for heads, the "average outcome" is 0.7. This doesn't mean you'll ever observe 0.7—it means over many flips, the average approaches 0.7.

For variance, recall that Var(X) = E(X²) - [E(X)]².

First, find E(X²):

  • When X=0: 0² = 0
  • When X=1: 1² = 1

So E(X²) = 0·(1-p) + 1·p = p

Therefore: Var(X) = p - p² = p(1-p)

What Does This Mean?

The variance p(1-p) measures uncertainty. Notice:

  • When p=0.5 (fair coin), variance = 0.25 (maximum uncertainty)
  • When p approaches 0 or 1 (almost certain outcome), variance approaches 0 (minimal uncertainty)
  • The standard deviation is √[p(1-p)]

Key Takeaway: For a Bernoulli random variable, the mean E(X)=p represents the probability of success, while the variance Var(X)=p(1-p) quantifies the uncertainty, reaching maximum at p=0.5 and minimum at the extremes.