MGF of the Poisson Explained with Worked Examples

For the moment generating function is .

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 MGF of the Poisson means

It comes from summing the series , using the exponential series. For and : . Differentiating at 0 gives and , hence the variance (mean and variance of a Poisson variable).

Independent Poisson variables with means 2 and 1 have the product , the MGF of a Poisson with mean 3: this proves that sums of independent Poissons are Poisson (sums of independent Poisson variables). The general theory is in the moment generating function.

With and the binomial MGF tends to , proving the Poisson approximation (the binomial MGF, the Poisson approximation to the binomial). The distribution itself is in the Poisson distribution.

What is it used for?

The Poisson MGF is a double exponential, and multiplying two of them adds the means.

How to use mgf of the poisson

  1. Write the Poisson probabilities .
  2. Sum times them to get .
  3. Differentiate and set for moments.
  4. Multiply MGFs for independent sums.

Graph

MGF exp(3(eᵗ − 1)) of a Poisson variable with mean 3M(0) = 1t = 0.5: 7.0018-2-1.5-1-0.500.5105101520MGF exp(3(eᵗ − 1)) of a Poisson variable with mean 3tM(t)M(t)Graph with x from -2 to 1 and y from 0 to 22. Shows the curve M(t); point M(0) = 1 at (0, 1); point t = 0.5: 7.0018 at (0.5, 7.0018).

The slope at t = 0 is the mean 3.

Worked examples

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

Example 1: M(0.5)

Find for .

Worked example
Answer
7.00187.0018
  1. Exponent
  2. Value

Example 2: second moment

Find for from .

Worked example
Answer
1212
  1. M″(0)

Example 3: a sum

Find the MGF at of the sum of independent Poisson variables with means 2 and 1.

Worked example
Answer
7.00187.0018
  1. Product

Special cases

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

λ = 2, t = 0.5

exp(2(e^0.5 − 1))

3.6598.

Mean

M′(0) = λ

2.

Variance

λ

2.

Sum of Poissons

λ₁ + λ₂

2 + 3 = 5.

Word problems

For X ~ Poisson(λ), M(t) = exp(λ(e^t − 1)). The mean and variance are both λ, and independent Poissons add their rates.

Evaluate M

Find M(0.5) for λ = 2.

  1. exp(2 × 0.6487)
  2. Check: ✓3.6599

Mean

Find the mean for λ = 2.

  1. M′(0) = λ
  2. Check: ✓2

Variance Higher

Find the variance.

  1. λ
  2. Check: ✓2

Sum Higher

Find the rate of Poisson(2) + Poisson(3).

  1. 2 + 3
  2. Check: ✓5

Common mistakes

λ(e^t) without −1

wrong ✗

λ(e^t − 1) ✓

M(0) must be 1.

Variance λ²

wrong ✗

variance = λ ✓

Mean equals variance.

Multiplying rates

λ₁λ₂ ✗

λ₁ + λ₂ ✓

Rates add.

M(0) ≠ 1

check ✗

exp(0) = 1 ✓

Sanity check.

Exam tips

  1. exp(λ(e^t − 1)).
  2. Mean = variance = λ.
  3. Rates add.
  4. M(0) = 1.
  5. Limit of the binomial.

Practice questions

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

1. M(1) for λ = 1 to 4 d.p. Foundation

5.5749

2. M(0.5) for λ = 3 to 4 d.p. Foundation

7.0018

3. M(−1) for λ = 2 to 4 d.p. Foundation

0.2825

4. Mean of Poisson(4.5) Higher

4.5

5. Sum rate 1.5 + 2.5 Higher

4

6. M(0.1) for λ = 5 to 4 d.p. Higher

1.6919

Practice generator

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

Solve: …

Key terms

Poisson MGF
exp(λ(e^t − 1)).
Rate (λ)
Mean count.
Independent sum
Rates add.
Equidispersion
Mean = variance.
Exponential series
Σ xⁿ/n!.
Moment
E(Xⁿ).

Frequently asked questions

What is the Poisson MGF?

exp(λ(e^t − 1)).

What are its mean and variance?

Both λ.

What is the sum of independent Poissons?

Poisson with the sum of rates.

How is it derived?

From the exponential series.

Which page covers the binomial MGF?

MGF of the binomial.

Which page covers the normal MGF?

MGF of the normal.

More in Advanced statistics and stochastic processes and the formula sheets.