Poisson Expected value using power series

528 Views Asked by At

The general calculation for the expected value of Poisson is clear to me.

$$\sum_{x=0}^\infty x*\frac{(\lambda^{x}*e^{-\lambda})}{x!} =...= \lambda$$

Generally proofs declare as their first step that $x=0$ results in a zero term, therefore the above can be written as:

$$\sum_{x=1}^\infty x*\frac{(\lambda^{x}*e^{-\lambda})}{x!} $$

Can't I simply leave x going from zero to $\infty$? My intuitive approach would have been:

$$\sum_{x=0}^\infty x*\frac{(\lambda^{x}*e^{-\lambda})}{x!} =e^{-\lambda}*\sum_{x=0}^\infty x*\frac{(\lambda^{x})}{x!} $$

Using the power series I can then proceed to:

$$e^{-\lambda}*\sum_{x=0}^\infty x*e^\lambda = \sum_{x=0}^\infty x $$

I definitely made a mistake somewhere along the way because the above is not $\lambda$. However, I'm not sure at what stages my thinking went wrong. Any pointers would be greatly appreciated.

Thanks!

1

There are 1 best solutions below

0
On BEST ANSWER

Comment posted as answer, as requested:

It went wrong in going from $\sum_{x=0}^\infty x \frac{\lambda^x}{x!}$ to $\sum_{x=0}^\infty x e^\lambda$. I don't know why you would think this is the case. $e^\lambda$ is not $\lambda x/x!$, it's the sum of that from $x=0$ to $\infty$.