Mgf of a random variable with added constant

Click For Summary
SUMMARY

The moment generating function (MGF) of a random variable Y, defined as Y = Z + c where Z follows an exponential distribution with parameter λ, can be calculated using the expectation E[e^{tY}] = E[e^{t(Z+c)}]. The integral method initially attempted was incorrect due to the use of f(z+c) instead of the proper f(z) in the integration. The discussion emphasizes the importance of transforming random variables into known forms to simplify calculations in probability and statistics.

PREREQUISITES
  • Understanding of moment generating functions (MGFs)
  • Knowledge of exponential probability density functions (PDFs)
  • Familiarity with expectation calculations in probability theory
  • Basic concepts of random variable transformations
NEXT STEPS
  • Study the properties of moment generating functions in detail
  • Learn about the Jacobian transformation technique in probability
  • Explore the derivation of moment generating functions for various distributions
  • Investigate applications of MGFs in statistical inference and hypothesis testing
USEFUL FOR

Students and professionals in statistics, mathematicians, and anyone working with probability theory who seeks to deepen their understanding of moment generating functions and random variable transformations.

WantToBeSmart
Messages
10
Reaction score
0
Hey,

I have a pdf of a random variable Z given. I am being asked to calculate what the moment generating function of a r.v Y= Z + c will be where c is a constant in ℝ

I tried to calculate it in the following way:

\int^∞_0 e^{(z+c)t} f(z+c)dz where f(z) is an exponential pdf with parameter λ.

but it proved to be an unsuccessful method. Could anyone please show me the right direction? I know I could use Jacobian transformation but I'm sure there is an easier method.

Thank you in advance!
 
Physics news on Phys.org
I wouldn't even mess around with the integral. Here is something I would try:

Y = Z + c where Z ~ exp(\lambda) and c is a constant. Then,

E[e^{tY}] = E[e^{t(Z+c)}]

Now do you see what you might be able to do?
 
Robert1986 said:
I wouldn't even mess around with the integral. Here is something I would try:

Y = Z + c where Z ~ exp(\lambda) and c is a constant. Then,

E[e^{tY}] = E[e^{t(Z+c)}]

Now do you see what you might be able to do?

I think it definitely solves this problem! Now I can proceed with the rest of the exercise. Thank you Robert!
 
You're most certainly welcome.

As a side note, this sort of thing is a rather valuable technique in prob/stat. That is, if you want to know about a certain RV, or a certain expectation, lots of times it is best to work it into some form you already know.
 
WantToBeSmart said:
I think it definitely solves this problem! Now I can proceed with the rest of the exercise. Thank you Robert!

Of course, you would have gotten the same result had you used the correct f(z) dz in your integration, instead of your _incorrect_ f(z+c) dz.

RGV
 
Ray Vickson said:
Of course, you would have gotten the same result had you used the correct f(z) dz in your integration, instead of your _incorrect_ f(z+c) dz.

RGV

Checked that and it was another mistake I was making. Thank you for pointing this out!
 

Similar threads

  • · Replies 10 ·
Replies
10
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 1 ·
Replies
1
Views
1K
  • · Replies 7 ·
Replies
7
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 5 ·
Replies
5
Views
2K
  • · Replies 9 ·
Replies
9
Views
2K
  • · Replies 2 ·
Replies
2
Views
2K
  • · Replies 1 ·
Replies
1
Views
1K
  • · Replies 6 ·
Replies
6
Views
5K