As the title says, I got an exercise I don't know how to approach:

Let $X$ be a normal random variable, with Expected value of 12 and Variance of 4.

Find $C$ such that $P(X > C) = 0.1 $

How should I approach such question? First time I see the difinitions Expected value, variance.

Thanks in advance.

  • $\begingroup$ This is the same as finding $C$ such that $P\{X \le C \} = 0.9$. $\endgroup$
    – copper.hat
    Dec 5, 2014 at 20:19
  • $\begingroup$ So what do you know about normal random variables (other than they are a kind of random variable that are normal instead of abnormal) $\endgroup$ Dec 5, 2014 at 20:26

1 Answer 1


$P(X>C)=0.1\leftrightarrow P((X-12)/2>(C-12)/2)=0.1$

$\rightarrow P(Z >(C-12)/2)=0.1$, where $Z = (X-12)/2$

Z~standard normal, Z is normal since it is a linear combination of normal random independent variables, this can be proven using moment-generating functions. And you should check that the expectation of $(X-12)/2$ is 0 and that its variance is 1, for this you use the general rules for calculating expected value and variance.

$\rightarrow P(Z\le(C-12)/2)=1-0.1=0.9$

$\Phi^{-1}(0.9)=1.281552$, from tables

$\rightarrow (C-12)/2=1.281552\rightarrow C=14.56$

  • $\begingroup$ what do you mean by "linear combination of normal random variableS"? here there is just one variable. C is a constant: what do you mean by (C-12)/2 having a zero mean? what is $\Theta^{-1}$ etc $\endgroup$
    – Math-fun
    Dec 5, 2014 at 20:39
  • $\begingroup$ You can prove using moment generating functions that a linear combination of independent normal random variables+ a constant is also normally random variables, we have (X-12)/2=X/2-6, which is a linear combination of of 1 normal random variable and a constant. Even though in this case you really only need that if X is normal, then aX+b is also normal, where a and b are constants. $\endgroup$
    – user119615
    Dec 5, 2014 at 20:48
  • $\begingroup$ I meant to write X instead of C in (C-12)/2 that you meantion. The inverse function I posted is the inverse of the cumulative distribution function of the standard normal random variable: en.wikipedia.org/wiki/… $\endgroup$
    – user119615
    Dec 5, 2014 at 20:51

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.