Poisson approximation to the binomial
Studying this course? Keep your progress in one place.
Key facts
- For with large and small, .
- A guide: and .
- The parameter is , the binomial mean.
- The fit is poor when is not small, because the variance is then well below the mean.
Why approximate
When is small the binomial variance is close to its mean, just like a Poisson.
Finding for large is awkward, and binomial tables do not cover large . When is large and is small, the binomial distribution behaves very like a Poisson distribution, which is easier to use.
When is small, , so is close to the mean . A Poisson has variance equal to its mean.
- B(1000, 0.002)
- Po(2)
| Binomial B(n, p) | Poisson Po(λ) | |
|---|---|---|
| Mean | np | λ |
| Variance | np(1 − p) | λ |
| Variance close to mean when | p is small | always |
Binomial B(n, p)
- Mean:
- np
- Variance:
- np(1 − p)
- Variance close to mean when:
- p is small
Poisson Po(λ)
- Mean:
- λ
- Variance:
- λ
- Variance close to mean when:
- always
. What is the variance?
The approximation
If is large and is small, then .
As a guide, use it when and ; the smaller and larger , the better the fit. The parameter is , the binomial mean.
- B(60, 0.05)
- Po(3)
- B(n, p), n large, p small
Worked example
State a Poisson approximation for .
- 1
Check the conditions: and .
- 2
.
. Which Poisson approximation is correct?
Using the approximation
Once you have , work exactly as for any Poisson variable.
Use Poisson tables or the formula, rewriting inequalities in terms of . State the new distribution first.
For combined questions, such as 10 independent boxes, find the single-box probability with the approximation and then use the binomial or product rule for the boxes.
- B(200, 0.02)
- Po(4)
Worked example
. Use a Poisson approximation to find and .
- 1
, so .
- 2
.
- 3
From the tables, .
After approximating by , which expression gives ?
Judging accuracy
It is good when is large and is small, and poor otherwise.
The approximation is a model, so the answer is not exact. For the approximate is and the exact value is .
It gets worse when is larger or is small. A binomial variable can never exceed , while a Poisson variable has no upper limit; this is harmless when is large and is small.
- B(10, 0.4)
- Po(4)
| B(1000, 0.002) | B(10, 0.4) | |
|---|---|---|
| Mean | 2 | 4 |
| Variance | 1.996 | 2.4 |
| Good approximation? | Yes: variance close to mean | No: variance well below mean |
B(1000, 0.002)
- Mean:
- 2
- Variance:
- 1.996
- Good approximation?:
- Yes: variance close to mean
B(10, 0.4)
- Mean:
- 4
- Variance:
- 2.4
- Good approximation?:
- No: variance well below mean
Which binomial is best approximated by a Poisson distribution?
Try an exam question
. (a) Explain why a Poisson distribution is a suitable approximation. (b) Use it to find .
[4 marks]
- [1] is large and is small, so .
- [1].
- [1].
- [1].
That's the notes covered.
Carry on to the next subtopic.
Try a question
Which Poisson distribution is the best approximation to the distribution of ?
1 mark, marked against the mark scheme
Which Poisson distribution is the best approximation to the distribution of ?
1 mark, marked against the mark scheme