Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

A Poisson process has PDF

$$P(X=k)=\frac{e^{-\lambda t}(\lambda t)^k}{k!}$$

I'm trying to find an expression for:

  1. $E[X | \lambda, t]$
  2. Confidence intervals (i.e. find $\delta$ such that $P(\bar{x}-\delta<X<\bar{x}+\delta)=c$ for some $c$)

To find the expectation, I've noticed that

$$E[X]=\sum_{k=0}^{\infty} \frac{e^{-\lambda t}(\lambda t)^k k}{k!}=e^{-\lambda t}\sum_{k=0}^{\infty}\frac{(\lambda t)^k}{(k-1)!}$$

But I have no idea how to go further. I read on wikipedia that the mean of a Poisson distribution is $\lambda$ - does this mean that the mean of a Poisson process is just $\lambda t$? And similarly its variance I suppose?

EDIT: I made some more progress based on procrastinator's comment, but I think I made a mistake.

Let $x=\lambda t$ and define $(-n)!=(n!)^{-1}$. Then we have


Which does not appear to equal $x$ as it should. Where did I go wrong?

share|improve this question
You are correct, the mean and variance are $\lambda t$. The proof follows analogously as in the case where the mean and variance are $\lambda$. The basic idea is to factorise $\lambda t$ outside the series and re-arranging the indices. – user10525 Dec 22 '12 at 19:51
@Procrastinator: Thanks this helps! Can you see the error in my edit? – Xodarap Dec 22 '12 at 22:14
There is a little mistake, for $k=0$, the first terms vanishes. Just takes this into account while rewriting the series. – user10525 Dec 22 '12 at 22:28
Oh I see, it's sort of $0/0!$, which my rewriting as $(k-1)!$ masked. (and it's $e^{-x}$, not $e^x$). If you want to put that as an answer, I'll accept. – Xodarap Dec 22 '12 at 22:59
I would prefer you to write the solution you have got. I would certainly upvote it. – user10525 Dec 22 '12 at 23:03
up vote 1 down vote accepted

Let $x=\lambda t$ for simplicity. Then we have:

$$\begin{eqnarray} \sum_{k=0}^{\infty}\frac{x^{k}e^{-x}k}{k!} &=& e^{-x}\sum_{k=1}^{\infty}\frac{x^{k}k}{k!} \\ &=& e^{-x}x\sum_{k=1}^{\infty}\frac{x^{k-1}}{(k-1)!} \\ &=& e^{-x}x\sum_{k=0}^{\infty}\frac{x^{k}}{k!} \\ &=& x \end{eqnarray}$$

Where the last step uses the Taylor Series expansion for $e^x$.

(Thanks Procrastinator for your help!)

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.