← 🔔 Standard Distributions
Subtopic 2 of 6

4.2Bernoulli and binomial

The idea

The binomial distribution counts successes in n independent trials, each succeeding with probability p. It is the answer to "exactly k out of n".

Think of it like this: Flip a (possibly unfair) coin n times and count the heads.

Why it exists

Binomial is the most-used discrete distribution: it covers all-succeed, exactly-k and "how many" questions.

How it works

  1. P(k successes) = C(n, k) pᵏ (1 − p)ⁿ⁻ᵏ.
  2. Mean = np; variance = np(1 − p).
  3. n = 1 is the Bernoulli distribution (mean p, variance p(1 − p)).
  4. All n succeed: pⁿ.
  5. The most likely value is near (n + 1)p.

Worked example: GATE 2021: biased coin, P(head) = 0.4, 1000 tosses; standard deviation of the heads

Variance = np(1 − p) = 1000 × 0.4 × 0.6 = 240, so the SD = √240 ≈ 15.49. Set n = 30 and p = 0.4 in the lab to see the shape.

Now play with it

  • →Set n = 10, p = 0.5: the bars are symmetric around 5.
  • →Increase p to 0.9 and watch the bars lean right; read the mean np.
0123456789100.27

Dashed line = mean. Shaded/green part = the range below.

mean E[X]5
variance2.5
standard deviation1.5811
P(2 ≤ X ≤ 5)0.6123

Number of successes in n independent trials, each with success probability p. n = 1 is the Bernoulli distribution.

Check yourself

A die is rolled three times. P(exactly one six)?

Remember: Binomial(n, p): C(n, k)pᵏ(1 − p)ⁿ⁻ᵏ, mean np, variance np(1 − p).
Exam notes (the dense version)

Bernoulli(p): one trial, mean p, variance p(1 − p). Binomial(n, p): number of successes in n independent trials, P(k) = C(n, k) pᵏ (1 − p)ⁿ⁻ᵏ, mean np, variance np(1 − p). The most likely value (mode) is near (n + 1)p.

Previous year questions: Standard Distributions (8)

PYQs are grouped by topic, so this is the full set for Standard Distributions; try the ones that match this subtopic. Open all 8 on the topic page.