Calculating the Variance for X^2: How to Find the Correct Solution

  • Thread starter Thread starter Addez123
  • Start date Start date
  • Tags Tags
    Variance
Join the discussion
Registration is free. Ask a follow-up in this thread, or start your own.
5 replies · 2K views
Addez123
Messages
199
Reaction score
21
Homework Statement
X is equally distributed along the intervall [0,1]
Calculate variance for X^2
Relevant Equations
Variance:
$$\int (x-u)^2*fx(x) dx$$
At first I assumed u to be 1/2 since X is equally distributed along 0-1.
$$\int (x-1/2)^2*x^2 dx = 1/30$$
The correct answer should be 4/45.

I would calculate the u but I think I do it wrong.
If fx(x) = x^2 then what is g(x)?

fx is the probability density function, which is the x^2 they supplied, right?
g(x) i have no real definition for.
 
Physics news on Phys.org
Addez123 said:
fx(x) = x^2
This is not the pdf of a uniform distribution on [0,1]
 
Orodruin said:
This is not the pdf of a uniform distribution on [0,1]
So g(x) = x^2, and fx(x) = 1?
Because then you get u = 1/3rd and variance = 1/9th :/
 
Addez123 said:
So g(x) = x^2, and fx(x) = 1?
Because then you get u = 1/3rd and variance = 1/9th :/
Show how you are computing the variance.
(I think it is easiest to use E(X2)-(E(X))2.)
 
  • Like
Likes   Reactions: Delta2
$$\int (x-1/3)^2 * 1 dx$$
from 0 to 1
EDIT: It should say x^2 since we're donig variance for v(x^2) not v(x). That gives the correct solution.
 
Last edited:
Addez123 said:
$$\int (x-1/3)^2 * 1 dx$$
from 0 to 1
EDIT: It should say x^2 since we're donig variance for v(x^2) not v(x). That gives the correct solution.
Yes.