0
$\begingroup$

For instance, given $\DeclareMathOperator{\P}{\mathbb{P}} \DeclareMathOperator{\E}{\mathbb{E}} G(z) = \E z^X$, what exactly is $z$? and also what does the generating function actually give you? Because it states that it is returning the expected value of $z^X$ but how exactly is that helpful?

$\endgroup$
0
$\begingroup$

$z$ is nothing of importance, it's simply a variable. Just as the moment generating function $M_X(t)$ is a function in $t$, the probability function $G_X(z)$ is a function in $z$.

The use of generating functions for a discrete probability distribution is that $G_X(z)$ can be used to obtain the probabilities that define the random variable.

You can retrieve the probability $X=k$ by differentiating $G_X(z)$ a total of $k$ times and using the formula:

$$P(X=k) = \frac{G^{(k)}(0)}{k!}$$

So we simply end up evaluating the generating function at $0$ like with the moment generating function.

It follows if we can show $X$ and $Y$, discrete rv, have the same probability generating function, then they have the same distribution.

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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