Expectation of 2 random variable, E(|X-Y|^a)

In summary, the question asks for the expectation value of the absolute value of the difference between two independent uniform random variables over the interval [0,1]. The joint probability distribution for these variables is constant and can be determined through normalization. The integral involving the absolute value can be split into two separate integrals over the upper and lower triangles of the square, with the boundary being the diagonal line y=x. Using a variable substitution, the indefinite integral can be computed and then evaluated at the limits to find the expectation value.
  • #1
Micle
5
0
Hi, anyone help please.

Let X and Y are independent uniform random variables over the interval [0,1]
E[|X-Y|a]=?

where, a>0
 
Physics news on Phys.org
  • #2
Do you have any restrictions on a? Is it integer or any real number?

I suggest you start with the definition of the expectation value... you sum or integrate over values times the probability distribution:

[tex] E(g(X,Y)) = \int_{x,y\in[0,1]} g(x,y)\cdot f(x,y) dxdy[/tex]
where f(x,y) is the joint probability distribution. Since X and Y are both uniform the joint distribution will be f(x,y) = constant. You can determine this constant by normalization:
[tex] \int_{x,y\in [0,1]} f(x,y) dx dy = 1[/tex]

As far as doing the integral involving the absolute value you should break the square over which you are integrating into the region where (x-y)>0 and (x-y)<0.
 
  • #3
The exercise doesn't tell that a is interger or real number, then I just consider it as real number.

As your suggestion, I do following,
Let Z = X-Y, where |Z|>0 and Z [tex]\in[/tex][-1,1]

E[|Z|a] = [tex]\int[/tex][tex]^{1}_{-1}[/tex]Zadz
= [tex]\int[/tex][tex]^{1}_{0}[/tex]Zadz - [tex]\int[/tex][tex]^{0}_{-1}[/tex]Zadz
= [tex]\frac{1}{a+1}[/tex] - [tex]\frac{1}{a+1}[/tex](-1)a+1

=[tex]\frac{1}{a+1}[/tex](1-(-1)a+1).

Sorry for my poorness, this is corrected or not?
 
  • #4
Not quite. You still have to integrate over an area so you need two variables. I would stick to x and y but use the substitution for for finding indefinite integral.

Consider the area over which you must integrate is the square 0<x<1,0<y<1.
|y
|___
|...|
|___|___ x

The boundary at which the absolute value changes from equal, to negative of is the line y=x which is the diagonal of this square.

You integrate over each of the two triangles separately.
__
| / /|
|/ / | (hope the spacing comes out right)
In the upper triangle y>x so |x-y| = (y-x).
In the lower triangle x>y so |x-y| = (x-y).

So integrate |x-y|^a over each triangle making the above substitutions.

Something like:
[tex]\int_{y=0}^1\int_{x=0}^y(y-x)^a dx dy[/tex]
for the lower triangle.
You may use (z=x-y) or (z=y-x) as a variable substitution to do the indefinite integrals but convert your answer back to x's and y's to evaluate at the limits.
 
  • #5
Thanks for your advice, let me try!
 

FAQ: Expectation of 2 random variable, E(|X-Y|^a)

What is the formula for calculating the expectation of two random variables?

The formula for calculating the expectation of two random variables, X and Y, is E(|X-Y|^a) where a is any real number.

What is the significance of calculating the expectation of two random variables?

Calculating the expectation of two random variables helps determine the average value of the absolute difference between the two variables. This can provide insights into the relationship between the variables and their potential impact on each other.

Can the expectation of two random variables be negative?

Yes, the expectation of two random variables can be negative. This can occur if the absolute difference between the two variables is mostly negative, resulting in a negative average value.

How is the expectation of two random variables affected by the value of a?

The value of a affects the expectation of two random variables by determining the degree of emphasis placed on larger differences between the variables. A larger value of a will result in a higher expectation, indicating a greater average difference between the variables.

Are there any limitations to using the expectation of two random variables?

One limitation of using the expectation of two random variables is that it only considers the average difference between the variables and does not take into account the overall distribution of their values. It is important to also consider other statistical measures to fully understand their relationship. Additionally, this formula may not be applicable for all types of random variables.

Back
Top