Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

This is a more general question about the transformation of a random variable. Say X is given as a certain distribution, and Y=g(X). If it asks to compute the pdf of Y, I am having trouble to determine the region of pdf of Y. (sorry I know this is confusing, let me have one example).

example: say Z is exponential (parameter 1/2), Y=exp(Z).

Then the cdf of Y=P(Z< lnz), pdf_Y =d/dz[ cdf_Y]=z^(-3/2). My question is what region does this answer defined?

share|cite|improve this question
up vote 2 down vote accepted

The random variable $Z$ of your question has density function $e^{-z/2}$ for $z\gt 0$ and $0$ for $z\lt 0$.

By your argument, we have $$\Pr(Y\le y)=\Pr(e^Z\le y).$$ If $y\le 1$, then $\Pr(e^Z\le y)=0$, since $Z\le 0$ with probability $0$. Thus the density function of $Y$ is $0$ for $y\le 1$.

If $y\gt 1$, then $$\Pr(e^Z\le y)=\Pr(Z\le \ln y)=1-e^{-(\ln y)/2}.$$ Differentiate. For $y\gt 1$, the density of $Y$ is $\frac{1}{2y}e^{-(\ln y)/2}$, which is $\frac{1}{2}y^{-3/2}$.

Thus, as is often the case in probability theory, the density function of $Y$ is defined by different expressions on different parts of its domain.

share|cite|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

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