Normal Approximation to the Binomial Explained with Worked Examples

For large , , using a continuity correction of .

Write 2x or 2*x to multiply, ^ for powers, and ; between simultaneous equations. You can also type factor, expand, derivative of, integrate … from a to b, limit … as x->0 or 15% of 80.

Try an example

Before you start

This page is easier if you are comfortable with:

What Normal approximation to the binomial means

When is large and is not too close to 0 or 1 (so that and ), the binomial distribution is well approximated by a normal distribution with the same mean and variance .

Since the binomial is discrete and the normal is continuous, apply a continuity correction: becomes , and becomes .

Standardise and use normal tables.

This page is part of Probability distributions in Statistics. Topics that work alongside it: Binomial distribution, Mean and variance of a binomial, Normal distribution: standardising, Hypothesis test for the mean of a normal, Product moment correlation coefficient and Normal distribution: density.

What is it used for?

When n is large and p is not close to 0 or 1, a binomial distribution B(n, p) is approximately normal with mean np and variance np(1 − p). A continuity correction improves the approximation.

How to use normal approximation to the binomial

  1. Check that and are both large enough.
  2. Find the mean and variance .
  3. Apply the continuity correction.
  4. Standardise and find the probability.

Graph

B(20, 0.5) and its normal approximation0246810121416182000.020.040.060.080.10.120.140.160.180.2B(20, 0.5) and its normal approximationxyN(10, 5)Graph with x from -0.5 to 20.5 and y from 0 to 0.2. Shows bars (21); the curve N(10, 5).

The bars are the exact binomial probabilities. The curve is the normal distribution with the same mean np = 10 and variance np(1 − p) = 5.

Worked examples

These examples are worked by hand, step by step, so you can compare your own working.

Example 1: find the parameters

For , find the mean and variance of the normal approximation.

Worked example
Answer
N(40, 24)N(40,\ 24)
  1. Mean
  2. Variance

Example 2: approximate a probability

Estimate for .

Worked example
Answer
≈0.869\approx0.869
  1. Approximating distribution
  2. Continuity correction
  3. Standardise
  4. Read from tables

Example 3: B(50, 0.5)

For , find the mean and standard deviation of the normal approximation.

Worked example
Answer
μ=25, σ≈3.54\mu = 25,\ \sigma \approx 3.54
  1. Mean
  2. Variance
  3. Standard deviation

Special cases

A few situations come up again and again. Knowing them saves time and helps you spot answers that cannot be right.

B(100, 0.5)

mean np

50.

same

variance np(1 − p)

25.

P(X ≤ 55)

z = (55.5 − 50)/5

1.1.

B(40, 0.3)

variance

8.4.

Word problems

B(n, p) ≈ N(np, np(1 − p)) for large n, using a continuity correction ±0.5. P(X ≤ k) uses k + 0.5; P(X ≥ k) uses k − 0.5.

Mean

B(100, 0.5).

  1. 100 × 0.5
  2. Check: ✓50

Variance

npq.

  1. 100 × 0.25
  2. Check: ✓25

z for X ≤ 55 Higher

Use 55.5, SD = 5.

  1. 5.5/5
  2. Check: ✓1.1

B(40, 0.3) Higher

npq.

  1. 40 × 0.21
  2. Check: ✓8.4

Common mistakes

No continuity correction

55 ✗

55.5 ✓

Discrete to continuous.

SD = variance

25 ✗

5 ✓

Square root.

Poor when np small

always fine ✗

need np, nq > 5 ✓

Condition.

Wrong direction of ±0.5

k − 0.5 for ≤ ✗

k + 0.5 for ≤ ✓

Include k.

Exam tips

  1. μ = np, σ² = npq.
  2. Continuity ±0.5.
  3. Standardise.
  4. Check np > 5 and nq > 5.
  5. Sketch the area.

Practice questions

Try each one on paper, then open the answer. Use the solver above to see the full working.

1. Mean of B(80, 0.25) Foundation

20

2. Variance of B(80, 0.25) Foundation

15

3. z for P(X ≤ 22), B(80, 0.25), 4 dp Foundation

0.6455

4. z for P(X ≥ 30), B(100, 0.4), 4 dp Higher

-2.1433

5. SD of B(200, 0.5), 4 dp Higher

7.0711

6. z for P(X ≤ 48), B(100, 0.5) Higher

-0.3

Practice generator

Unlimited fresh questions with instant marking. Choose a level, work it out on paper, then type your answer.

Solve: …

Key terms

Normal approximation
N(np, npq).
Continuity correction
±0.5.
Mean
np.
Variance
npq.
Standardise
z = (x − μ)/σ.
Discrete
Whole numbers.

Frequently asked questions

When can I use the normal approximation?

When n is large and np, nq > 5.

What are the parameters?

Mean np and variance np(1 − p).

What is a continuity correction?

Adjusting by 0.5 because the binomial is discrete.

How do I find P(X ≤ k)?

Use k + 0.5 in the normal.

Which page covers the binomial?

binomial distribution.

Which page covers standardising?

standardising a normal.

More in Statistics and the formula sheets.