1
$\begingroup$

Let $X$ be a random variable that is normally distribted with mean $\mu$ and variance $\sigma^2$. Compute

  1. $E(X^2)$
  2. $E(X^4)$
  3. $Var(X^2)$

They also hint that for a standard normally distributed random variable $Z$ it follows that $E(Z^4)=3$.

I don't see how to use the hint given

$\endgroup$
  • $\begingroup$ How would you write $X$ in term of $Z$? $X = . \times Z + . $ $\endgroup$ – Max Apr 26 '18 at 17:51
  • $\begingroup$ Z-score I suppose? $X=Z \sigma + \mu?$ $\endgroup$ – Parseval Apr 26 '18 at 18:01
  • $\begingroup$ Yea exactly now try to plug this equation in your expectation and work with the linearity of the expectation $\endgroup$ – Max Apr 26 '18 at 18:02
  • $\begingroup$ I get to $$E(X^2)=E((Z\sigma+\mu)^2)=E(Z^2\sigma^2+2Z\sigma+\mu^2)=\sigma^2E(Z^2)+2\sigma\mu E(Z)+\mu^2.$$ Is it generally true that $E(Z^k)=k-1?$ In that case then the answer should be $$E(X^2)=\sigma^2+\mu^2?$$ $\endgroup$ – Parseval Apr 26 '18 at 19:02
  • $\begingroup$ @Parseval : It is not generally true that $\operatorname E(Z^k) = k-1,$ but your conclusion that $\operatorname E(X^2) = \mu^2+\sigma^2$ is correct. $\qquad$ $\endgroup$ – Michael Hardy Apr 26 '18 at 19:06
2
$\begingroup$

$\newcommand{\e}{\operatorname{E}}$\begin{align} \e(X^4) & = \e((\mu+\sigma Z)^4) \\[10pt] & = \e(\mu^4 + 4\mu^3\sigma Z + 6\mu^2\sigma^2 Z^2 + 4 \mu\sigma^3 Z^3 + \sigma^4 Z^4) \\[10pt] & = \mu^4 + 4\mu^3\sigma \e(Z) + 6\mu^2\sigma^2 \e(Z^2) + 4\mu \sigma^3 \e(Z^3) + \sigma^4 \e(Z^4). \end{align} Now apply what you were given about the expected values of powers of $Z.$

$\endgroup$
  • $\begingroup$ Thanks! Can you plese check if my answer to a comment above is correct? $\endgroup$ – Parseval Apr 26 '18 at 19:06
  • 1
    $\begingroup$ +1 for your comments above ! $\endgroup$ – Max Apr 26 '18 at 20:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.