In a lot of sources, such as the Wikipedia page for log-normal distributions, the cumulative distribution function for log-normal distributions is denoted as

$$F_X(x)=\Phi\left(\frac{\ln x-\mu}{\sigma}\right)$$

where $\Phi$ is the cumulative distribution function of a normal distribution. That is, if $Z$ is normally distributed, its CDF is

$$\Phi(z)=\frac{1}{\sqrt{2\pi}}\int^x_{-\infty}\exp \left(-\frac{1}{2}\cdot z^2\right)dz.$$

This might be a stupid questions but I am not sure what the CDF for the log-normal distribution actually means. Is it

$$F_X(x)=\Phi\left(\frac{\ln x-\mu}{\sigma}\right) \\ =\frac{1}{\sqrt{2\pi}}\int^x_{-\infty}\exp \left(-\frac{1}{2}\cdot\left(\frac{\ln x-\mu}{\sigma}\right)^2\right)dz$$ and is there a way to derive the CDF for log-normal distribution without using its probability density function? Is the CDF of a log-normal distribution the logarithm of the CDF for normal distribution?


You write: $$\Phi(z)=\frac{1}{\sqrt{2\pi}}\int^x_{-\infty}\exp \left(-\frac{1}{2} z^2\right)dz$$which is wrong.

It should be:$$\Phi(z)=\frac{1}{\sqrt{2\pi}}\int^z_{-\infty}\exp \left(-\frac{1}{2} x^2\right)dx$$or - switching the variables $z,x$:$$\Phi(x)=\frac{1}{\sqrt{2\pi}}\int^x_{-\infty}\exp \left(-\frac{1}{2} z^2\right)dz$$

This leads to $$F_X(x)=\frac{1}{\sqrt{2\pi}}\int^{\frac{\ln x-\mu}{\sigma}}_{-\infty}\exp \left(-\frac{1}{2} z^2\right)dz=\int^{\frac{\ln x-\mu}{\sigma}}_{-\infty}\phi(z)dz$$where $\phi$ denotes the PDF of standard normal distribution.

PDF $f_X$ can be found by differentiating the CDF which leads to:$$f_X=\frac1{x\sigma}\phi\left(\frac{\ln x-\mu}{\sigma}\right)=\frac1{x\sigma\sqrt{2\pi}}\exp\left(-\frac{(\ln x-\mu)^2}{2\sigma^2}\right)$$

| cite | improve this answer | |

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.