I'm trying to derive the distribution of a random variable $Y$ given that I know the distribution of a random variable $X$ and the relationship they share.

The $pdf$ of $X$ is expressed as:

$ f_{X} = \begin{cases} 1/3 & \text{if -2 $<$ $x$ < 1}\\ 0 & \text{otherwise} \end{cases} $

I also know that $Y = g(X) = |{X}|$

In problems like this, I learned one must first calculate the $CDF$ of $Y$ and then derived in relation to $y$.

$F_{Y}(y) = \mathbb{P}( Y \le y) = \mathbb{P}(|X| \leq y) = \mathbb{P}( X < y) + \mathbb{P}( X \geq -y) $

Given that $Y$ is the absolute value of $X$, the inequality can be seen as the area of triangles (as far as I understand it).

But considering these are continuous random variables, I can't see how I'll integrate to find $\mathbb{P}(.)$


Here is a figure based on a simulation in R that suggests the answer. The simulation uses a million observations of $X \sim \mathsf{Unif}(-2,1).$ Then we show histograms of the samples of $X$ and of $Y = |X|.$

You have made a reasonable start on the formal derivation. Now, you need to express the right-hand side of the CDF of $Y$ as a function of $y$ and then take its derivative to get the PDF of $Y.$

 x = runif(10^6, -2, 1)                  # simulate sample of X's
 y = abs(x)                              # transform to get Y's
 par(mfrow=c(1,2))                       # make histogram of X's and of Y's
  hist(x, prob=T, br=12, col="skyblue2")
  hist(y, prob=T, br=12, col="skyblue2")

enter image description here

The plots below (based on Empirical CDFs of the two samples) suggest the linear functions that make up the CDFs of $X$ and $Y.$

enter image description here

| cite | improve this answer | |
  • $\begingroup$ This is an inventive solution, BruceET. Thank you. I was hoping for a more clear mathematical derivation. At least, the beginning of it so I could follow from there. =) $\endgroup$ – Mason Beau Mar 27 at 23:32

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.