FAQFAQ   SearchSearch   MemberlistMemberlist   UsergroupsUsergroups 
 ProfileProfile   PreferencesPreferences   Log in to check your private messagesLog in to check your private messages   Log inLog in 
Forum index » Science and Technology » Math » num-analysis
How to get the analytical PDF of this expression?
Post new topic   Reply to topic Page 1 of 1 [4 Posts] View previous topic :: View next topic
Author Message
glare22@gmail.com
science forum beginner


Joined: 12 Jul 2006
Posts: 7

PostPosted: Thu Jul 13, 2006 9:08 am    Post subject: How to get the analytical PDF of this expression? Reply with quote

Can anyone tell me the pdf of this expression u0+u1*x+u2(x^2-1)?
where u0,u1,u2 is constant. And x is a random variable satisfing the
normal distribution N(0,1). Thanks a lot.
Back to top
Torsten Hennig
science forum Guru Wannabe


Joined: 28 Apr 2005
Posts: 136

PostPosted: Thu Jul 13, 2006 10:46 am    Post subject: Re: How to get the analytical PDF of this expression? Reply with quote

Quote:
Can anyone tell me the pdf of this expression u0+u1*x+u2>(x^2-1)?
where u0,u1,u2 is constant. And x is a random variable >satisfing the
normal distribution N(0,1). Thanks a lot.

Hi,

let Y = u0 + u1*X + u2*(X^2-1).
For a in IR, calculate the X-values for which Y<=a.
(So solve u0 + u1*X + u2*(X^2-1) <= a for X).
Let the corresponding intervall be given by
[l(a),u(a)].
Then the pdf for Y , f_Y, is given by
f_Y(a) = f_X(u(a))*u'(a) - f_X(l(a))*l'(a).

Try the formula for Y = X^2.
You should arrive at
f_Y(a)=1/(2*sqrt(a))*(f_X(-sqrt(a))+f_X(sqrt(a))) (a>0).

Best wishes
Torsten.
Back to top
Duncan Muirhead
science forum addict


Joined: 08 Oct 2005
Posts: 70

PostPosted: Thu Jul 13, 2006 11:57 am    Post subject: Re: How to get the analytical PDF of this expression? Reply with quote

On Thu, 13 Jul 2006 02:08:33 -0700, glare22 wrote:

Quote:
Can anyone tell me the pdf of this expression u0+u1*x+u2(x^2-1)?
where u0,u1,u2 is constant. And x is a random variable satisfing the
normal distribution N(0,1). Thanks a lot.
If we assume u2>0 then

u0 + u1*x + u2*(x*x-1) = u2*y^2 + u0 - u1*u1/(4*u2) - u2
where y = x-u1/(2*u2) is a N(-u1/(2*u2), 1) variable.
y^2 has a non-central chi-square distribution with 1
degree of freedom, whose distribution function you can
find by searching the web (for non-central chi-square),
and then a linear transformation will get the distribution
of the variable you want.
Duncan
Back to top
glare22@gmail.com
science forum beginner


Joined: 12 Jul 2006
Posts: 7

PostPosted: Fri Jul 14, 2006 11:46 pm    Post subject: Re: How to get the analytical PDF of this expression? Reply with quote

Thank Torsten Hennig and Duncan Muirhead a lot.


Duncan Muirhead wrote:
Quote:
On Thu, 13 Jul 2006 02:08:33 -0700, glare22 wrote:

Can anyone tell me the pdf of this expression u0+u1*x+u2(x^2-1)?
where u0,u1,u2 is constant. And x is a random variable satisfing the
normal distribution N(0,1). Thanks a lot.
If we assume u2>0 then
u0 + u1*x + u2*(x*x-1) = u2*y^2 + u0 - u1*u1/(4*u2) - u2
where y = x-u1/(2*u2) is a N(-u1/(2*u2), 1) variable.
y^2 has a non-central chi-square distribution with 1
degree of freedom, whose distribution function you can
find by searching the web (for non-central chi-square),
and then a linear transformation will get the distribution
of the variable you want.
Duncan
Back to top
Google

Back to top
Display posts from previous:   
Post new topic   Reply to topic Page 1 of 1 [4 Posts] View previous topic :: View next topic
The time now is Thu Dec 14, 2017 4:59 pm | All times are GMT
Forum index » Science and Technology » Math » num-analysis
Jump to:  

Similar Topics
Topic Author Forum Replies Last Post
No new posts Integrate erf type expression Pratim Vakish num-analysis 4 Mon Jul 17, 2006 2:27 pm
No new posts Simplifying Algebraic expression Jeffrey Spoon Math 4 Wed Jul 12, 2006 3:04 pm
No new posts ? LS expression for A*x = b Cheng Cosine num-analysis 4 Tue Jul 11, 2006 11:27 pm
No new posts Advanced analytical methods for path integral calculation jaykov1 Particle 0 Tue Jul 11, 2006 2:36 am
No new posts Advanced analytical methods for path integral calculation. jaykov1 num-analysis 0 Sat Jul 08, 2006 11:36 pm

Copyright © 2004-2005 DeniX Solutions SRL
Other DeniX Solutions sites: Electronics forum |  Medicine forum |  Unix/Linux blog |  Unix/Linux documentation |  Unix/Linux forums  |  send newsletters
 


Powered by phpBB © 2001, 2005 phpBB Group
[ Time: 0.0199s ][ Queries: 16 (0.0033s) ][ GZIP on - Debug on ]