Find Cov(Z,W) with E(X^2)if X is N(0,1)

  • Context: MHB 
  • Thread starter Thread starter WMDhamnekar
  • Start date Start date
Click For Summary

Discussion Overview

The discussion revolves around finding the covariance between two expressions, Z and W, derived from independent standard normal random variables X and Y. Participants explore the implications of expected values and variances in the context of these random variables, as well as the distribution of a derived variable Y, which is the square of X.

Discussion Character

  • Technical explanation, Conceptual clarification, Debate/contested

Main Points Raised

  • One participant calculates Cov(Z,W) and expresses confusion about how E(X^2)E(Y^2) equals 1, given that E(X) is 0.
  • Another participant explains that since X is distributed as N(0,1), it follows that Var(X) = 1, leading to E(X^2) = 1.
  • There is a question regarding the variance of X^2, with a participant seeking clarification on its calculation.
  • A participant inquires about the distribution of Y = X^2, questioning whether it is normally distributed.
  • Another participant responds that Y is not normally distributed and introduces the concept of the chi-squared distribution related to the sum of squares of independent standard normal variables.

Areas of Agreement / Disagreement

Participants generally agree on the properties of the normal distribution and the calculations related to expected values and variances. However, there is a lack of consensus regarding the distribution of Y, with differing views on whether it is normal or follows a chi-squared distribution.

Contextual Notes

The discussion includes assumptions about the independence of random variables and the properties of the normal distribution, but does not resolve all mathematical steps related to the variance of X^2.

WMDhamnekar
MHB
Messages
379
Reaction score
30
Let X and Y be two independent \mathcal{N}(0,1) random variables and

Z=1+X+XY^2

W=1+X
I want to find Cov(Z,W).

Solution:-

Cov(Z,W)=Cov(1+X+XY^2,1+X)

Cov(Z,W)=Cov(X+XY^2,X)

Cov(Z,W)=Cov(X,X)+Cov(XY^2,X)

Cov(Z,W)=Var(X)+E(X^2Y^2)-E(XY^2)E(X)

Cov(Z,W)=1+E(X^2)E(Y^2)-E(X)^2E(Y^2)

Cov(Z,W)=1+1-0=2

Now E(X)=0, So E(X)^2E(Y^2)=0, But i don't follow how E(X^2)E(Y^2)=1? Would any member explain that? My another question is what is Var(X^2)?
 
Last edited:
Physics news on Phys.org
Re: E(x^2)and VAR(x^2)if X is N(0,1).

Dhamnekar Winod said:
My another question is what is Var(X^2)?

Hi Dhamnekar,

Let's start with this one.
It's the variance. It is the mean of the squared deviations from the average.
And the average of $X$ is the same thing as the expected value $E(X)$ or just $EX$.
In formula form:
$$\operatorname{Var}(X) = E\left((X - EX)^2\right)$$
If we write it out, we can find that it can be rewritten as:
$$\operatorname{Var}(X) = E(X^2) - (EX)^2$$

Dhamnekar Winod said:
Let X and Y be two independent \mathcal{N}(0,1) random variables and

(snip)

Now E(X)=0, So E(X)^2E(Y^2)=0, But i don't follow how E(X^2)E(Y^2)=1? Would any member explain that?

Now let's get back to your first question.

The fact that $X \sim \mathcal{N}(0,1)$ means that $\operatorname{Var}(X)=1$.
Combine it with $EX=0$ and fill it in:
$$\operatorname{Var}(X) = E(X^2) - (EX)^2 \implies 1=E(X^2)-0 \implies E(X^2)=1$$
 
Re: E(x^2)and VAR(x^2)if X is N(0,1).

Klaas van Aarsen said:
Hi Dhamnekar,

Let's start with this one.
It's the variance. It is the mean of the squared deviations from the average.
And the average of $X$ is the same thing as the expected value $E(X)$ or just $EX$.
In formula form:
$$\operatorname{Var}(X) = E\left((X - EX)^2\right)$$
If we write it out, we can find that it can be rewritten as:
$$\operatorname{Var}(X) = E(X^2) - (EX)^2$$
Now let's get back to your first question.

The fact that $X \sim \mathcal{N}(0,1)$ means that $\operatorname{Var}(X)=1$.
Combine it with $EX=0$ and fill it in:
$$\operatorname{Var}(X) = E(X^2) - (EX)^2 \implies 1=E(X^2)-0 \implies E(X^2)=1$$

Hello,
If $X$ be $\mathcal{N}(0,1)$ random variable, and $Y=X^2$ is the function of $X$, what is the distribution of $Y$?Is its distribution Normal?
 
Re: E(x^2)and VAR(x^2)if X is N(0,1).

Dhamnekar Winod said:
Hello,
If $X$ be $\mathcal{N}(0,1)$ random variable, and $Y=X^2$ is the function of $X$, what is the distribution of $Y$?

Is its distribution Normal?

No...

In probability theory and statistics, the chi-squared distribution (also chi-square or $χ^2$-distribution) with $k$ degrees of freedom is the distribution of a sum of the squares of $k$ independent standard normal random variables.
 

Similar threads

Replies
4
Views
1K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 43 ·
2
Replies
43
Views
6K
  • · Replies 17 ·
Replies
17
Views
3K
Replies
1
Views
3K
  • · Replies 9 ·
Replies
9
Views
2K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 24 ·
Replies
24
Views
3K
  • · Replies 14 ·
Replies
14
Views
2K
  • · Replies 5 ·
Replies
5
Views
2K