# probability generating functionsWatch

This discussion is closed.
#1
hopefully someone can help me out with this

Suppose the PGF of a RV Z is given by:

G_z(S) = (4-S) / (3)(4-3s)

Find the distribution of Z, that is, the probabilities
P(Z = i) for i = 0, 1, 2, . . . .

my tutor said something like get it into the form a + 1/(1-s) but i cant... help !
0
14 years ago
#2
(Original post by kikzen)
hopefully someone can help me out with this

Suppose the PGF of a RV Z is given by:

G_z(S) = (4-S) / (3)(4-3s)

Find the distribution of Z, that is, the probabilities
P(Z = i) for i = 0, 1, 2, . . . .

my tutor said something like get it into the form a + 1/(1-s) but i cant... help !
The Probability Generating Function (hereafter G_z(s)) is defined by the following:

G_z(S) = E_z(s^z) = Sum_[ i=0..infinity] s^(z_i)*f_z(z_i)

The probability f_z(z) = P(Z=z) is the coefficient of the zth power of S. Equate it all to (4-S) / (3)(4-3s) and get it in the form a + 1/(1-s) and it will be clear what it should look like from there.

If you still can't see it let me know.

Euclid.
0
#3
yah i know all that fool

it was just the rearranging but ive figured out the problem!
i was reading s/6 as 5/6. ah the joys of stupidity.

thanks anyway !
0
14 years ago
#4
(Original post by kikzen)
yah i know all that fool

it was just the rearranging but ive figured out the problem!
i was reading s/6 as 5/6. ah the joys of stupidity.

thanks anyway !
Lol sometimes it gets so bad that I cannot even read my own writing!

Euclid.
0
#5
Let p E (0, 1) and suppose that a RV X has
P(X = i) = p(1 − p)^i (i = 0, 1, 2, . . . )

Find the PGF for X, G_x(s) := E(s^x) for s E [0, 1].

Right well i wrote out the sum and that was a powerseries so G_x(s) =
p/(1-s(1-p))

Suppose that Y is independent but identically distributed to X.
so that means G_x(s) = G_y(s)

Deduce the PGF, G_(x+y) (s), for the sum X +Y .
well theyre equal so it is
[p/(1-s(1-p))]^2

Use the PGF to find the
mean of X +Y . By expanding GX+Y (s) as a power series in s, find the
distribution of X + Y .

this is where i get stuck. i know its another rearrangement but icant see how to do it at all, with the squareds everywhere!

help! (i may have done something wrong before so point that out and i might be able to figure it out ) danke!
0
14 years ago
#6
(Original post by kikzen)
Suppose that Y is independent but identically distributed to X.
so that means G_x(s) = G_y(s)
Are you sure they're equal? As Y is iid to X, then shouldn't G_y(s) = [G_x(s)]^n?

Euclid.
0
#7
why?
0
14 years ago
#8
(Original post by kikzen)
why?
Sorry I should have said G_y(s) = [G_x(s)]^(1/n)

Here's why.

Euclid.
0
X
new posts
Latest
My Feed

### Oops, nobody has postedin the last few hours.

Why not re-start the conversation?

see more

### See more of what you like onThe Student Room

You can personalise what you see on TSR. Tell us a little about yourself to get started.

### University open days

• University of East Anglia
All Departments Open 13:00-17:00. Find out more about our diverse range of subject areas and career progression in the Arts & Humanities, Social Sciences, Medicine & Health Sciences, and the Sciences. Postgraduate
Wed, 30 Jan '19
• Aston University
Wed, 30 Jan '19
• Solent University
Sat, 2 Feb '19

### Poll

Join the discussion

Remain (1065)
79.01%
Leave (283)
20.99%