Math Help Forum

Math Help Forum Feed Site Feed

Go Back   Math Help Forum > University Math Help > Advanced Probability and Statistics
Reply
 
Thread Tools Display Modes
  #1  
Old November 4th, 2009, 05:29 PM
Newbie
 
Join Date: Nov 2009
Posts: 4
Thanks: 0
Thanked 0 Times in 0 Posts
sasasa is on a distinguished road
Default desperate...moment generating function

f(x)=3/64x^2(4-x)

what is the moment generating function?
how do i find the mean and variance?

any help would really be appreciated since i dont understand anything concerning this

thankx
Reply With Quote
Advertisement
 
  #2  
Old November 4th, 2009, 05:55 PM
Danneedshelp's Avatar
Member
 
Join Date: Apr 2009
Posts: 170
Country:
Thanks: 73
Thanked 16 Times in 16 Posts
Danneedshelp is on a distinguished road
Default

Quote:
Originally Posted by sasasa View Post
f(x)=3/64x^2(4-x)

what is the moment generating function?
how do i find the mean and variance?

any help would really be appreciated since i dont understand anything concerning this

thankx
Do you mean f(x)=\frac{3}{64}x^{2(4-x)} ?
Reply With Quote
  #3  
Old November 4th, 2009, 06:18 PM
Junior Member
 
Join Date: Oct 2009
Posts: 65
Thanks: 13
Thanked 6 Times in 5 Posts
statmajor is on a distinguished road
Default

Var(x) = E(x^2) - E(x)^2

E(x) = M'(0)

E(x^2) = M''(0)

MGF of f(X) = E(e^{f(x)}) so you'll have to integrate e^{\frac{3}{64}x^{2(4-x)}} over a certain region.
Reply With Quote
  #4  
Old November 4th, 2009, 06:26 PM
Junior Member
 
Join Date: Oct 2009
Posts: 56
Thanks: 2
Thanked 20 Times in 19 Posts
theodds is on a distinguished road
Default

Quote:
Originally Posted by statmajor View Post
MGF of f(X) = E(e^{f(x)}) so you'll have to integrate e^{\frac{3}{64}x^{2(4-x)}} over a certain region.
This is not right. The moment generating function is defined as

M_X (t) = \mathbb{E}e^{Xt} = \int_{\mathbb{R}} e^{xt}f(x) dx

(for continuous distributions). I would help with the computation but I can't figure out what the density is supposed to be from the OP.
Reply With Quote
The Following 2 Users Say Thank You to theodds For This Useful Post:
Donate to MHF
  #5  
Old November 4th, 2009, 06:27 PM
mr fantastic's Avatar
Flow Master

 
Join Date: Dec 2007
Location: Zeitgeist
Posts: 12,237
Country:
Thanks: 2,574
Thanked 4,760 Times in 4,192 Posts
mr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond repute
Default

Quote:
Originally Posted by sasasa View Post
f(x)=3/64x^2(4-x)

what is the moment generating function?
how do i find the mean and variance?

any help would really be appreciated since i dont understand anything concerning this

thankx
I assume you mean f(x) = \frac{3}{64} x^2 (4 - x). This pdf is incomplete as you do not include the interval over which this expression is defined (the support).

You should know that you need to calculate E\left(e^{tX}\right) = \int e^{tx} \frac{3}{64} x^2 (4 - x) \, dx (and I have not included the integral terminals since you did not completely define the pdf). So please show all your working and clearly state where you are stuck.
__________________
There are two things you should never try to prove: the impossible and the obvious.

The greater danger for most of us lies not in setting our aim too high and falling short; but in setting our aim too low and achieving our mark. (Michelangelo Buonarroti)

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.
Reply With Quote
  #6  
Old November 4th, 2009, 06:28 PM
Junior Member
 
Join Date: Oct 2009
Posts: 65
Thanks: 13
Thanked 6 Times in 5 Posts
statmajor is on a distinguished road
Default

Darn, can't believe I wrote that. Thanks for correcting me.

But the other parts of my post should be right.

Thanks again.

Last edited by mr fantastic; November 4th, 2009 at 06:29 PM. Reason: m --> r
Reply With Quote
  #7  
Old November 5th, 2009, 04:21 AM
Newbie
 
Join Date: Nov 2009
Posts: 4
Thanks: 0
Thanked 0 Times in 0 Posts
sasasa is on a distinguished road
Default

Sorry (so many functions)… so overwhelmed that i even posted the wrong function. The right one is:
f(x)=0.15e^(-0.15(x-0.5)), when x is bigger or equal to 0.5
Thanks again for all your precious help
Reply With Quote
  #8  
Old November 5th, 2009, 05:01 AM
mr fantastic's Avatar
Flow Master

 
Join Date: Dec 2007
Location: Zeitgeist
Posts: 12,237
Country:
Thanks: 2,574
Thanked 4,760 Times in 4,192 Posts
mr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond repute
Default

Quote:
Originally Posted by sasasa View Post
Sorry (so many functions)… so overwhelmed that i even posted the wrong function. The right one is:
f(x)=0.15e^(-0.15(x-0.5)), when x is bigger or equal to 0.5
Thanks again for all your precious help
Can you set up the required integral using the definition of the moment generating function? Can you do the integration? Please show all that you can do and say where you're stuck.

(And please use normal size font so that we don't have to use microscopes to read it).
__________________
There are two things you should never try to prove: the impossible and the obvious.

The greater danger for most of us lies not in setting our aim too high and falling short; but in setting our aim too low and achieving our mark. (Michelangelo Buonarroti)

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.
Reply With Quote
  #9  
Old November 5th, 2009, 03:13 PM
Newbie
 
Join Date: Nov 2009
Posts: 4
Thanks: 0
Thanked 0 Times in 0 Posts
sasasa is on a distinguished road
Default

this is what i got:
Mx(t)=(-0.15e^(0.5t))/(t-0.15) but i am not sure if it is right

Can you please tell me if this is right:

Mean=E(X)=Mx´(0)=7.166

thanks

Last edited by sasasa; November 5th, 2009 at 05:07 PM.
Reply With Quote
  #10  
Old November 6th, 2009, 02:03 PM
mr fantastic's Avatar
Flow Master

 
Join Date: Dec 2007
Location: Zeitgeist
Posts: 12,237
Country:
Thanks: 2,574
Thanked 4,760 Times in 4,192 Posts
mr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond repute
Default

Quote:
Originally Posted by sasasa View Post
this is what i got:
Mx(t)=(-0.15e^(0.5t))/(t-0.15) but i am not sure if it is right

Can you please tell me if this is right:

Mean=E(X)=Mx´(0)=7.166

thanks
Your mgf is OK: - Wolfram|Alpha

I assume at this level you can correctly differentiate and substitute t = 0. You can check your own answer using the definition of E(X): Calculate 0.15 \int_{1/2}^{+\infty} x e^{-0.15(x - 0.5)} \, dx.
__________________
There are two things you should never try to prove: the impossible and the obvious.

The greater danger for most of us lies not in setting our aim too high and falling short; but in setting our aim too low and achieving our mark. (Michelangelo Buonarroti)

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.
Reply With Quote
  #11  
Old November 9th, 2009, 09:25 AM
Newbie
 
Join Date: Nov 2009
Posts: 4
Thanks: 0
Thanked 0 Times in 0 Posts
sasasa is on a distinguished road
Default

i think the mean is right...

did you get 0,25 as the variance?

thanks for all your help
Reply With Quote
  #12  
Old November 9th, 2009, 08:07 PM
mr fantastic's Avatar
Flow Master

 
Join Date: Dec 2007
Location: Zeitgeist
Posts: 12,237
Country:
Thanks: 2,574
Thanked 4,760 Times in 4,192 Posts
mr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond reputemr fantastic has a reputation beyond repute
Default

Quote:
Originally Posted by sasasa View Post
i think the mean is right...

did you get 0,25 as the variance?

thanks for all your help
I don't plan to do the calculation since you know how to answer the question. If you have found the correct values of E(X) and E(X^2) then your answer for Var(X) = E(X^2) - (E(X))^2 will probably be correct.
__________________
There are two things you should never try to prove: the impossible and the obvious.

The greater danger for most of us lies not in setting our aim too high and falling short; but in setting our aim too low and achieving our mark. (Michelangelo Buonarroti)

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.

  • To view links or images in signatures your post count must be 10 or greater. You currently have 0 posts.
Reply With Quote
  #13  
Old November 9th, 2009, 11:28 PM
Junior Member
 
Join Date: Oct 2009
Posts: 56
Thanks: 2
Thanked 20 Times in 19 Posts
theodds is on a distinguished road
Default

The random variable looks like a member of the location family of an exponential, i.e. if Z ~ Exponential(1/.15), X = Z + .5. That should simplify checking your answer.
Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off
Forum Jump


All times are GMT -7. The time now is 05:51 PM.


Powered by vBulletin® Version 3.7.3
Copyright ©2000 - 2009, Jelsoft Enterprises Ltd.
SEO by vBSEO 3.2.0 ©2008, Crawlability, Inc.
©2005 - 2009 Math Help Forum


Math Help Forum is a community of maths forums with an emphasis on maths help in all levels of mathematics.
Register to post your math questions or just hang out and try some of our math games or visit the arcade.