I'm trying to find the mean and variance of $Y = \max(X_1, ..., X_n)$ where $X_i \sim \mathcal{N}(\mu_i, \sigma^2)$.

Note that the $X_i$ are independent, but not identically distributed. That is, they have the same variance $\sigma^2$ but different means $\mu_i$.

The answer to my previous question may help: Distribution of maximum of normally distributed random variables.


1 Answer 1


Not the entire answer, but here's an observation.

For the $\max$ function, the CDF combines very easily. That is, the probability that $y < \Lambda$ equals the probability that all $x_i < \Lambda$. If furthermore the $X$ are independent then it is true that:

$$CDF_Y (\Lambda) = \prod_i^n \left[ CDF_{X_i}(\Lambda) \right]$$

At least formally you can suspect that this allows you to compute $CDF_Y$ and therefore $PDF_Y$.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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