I have $n$ different Normal Distribution $N_i = \mathcal{N}(\mu=\mu_i, \sigma=\sigma^*)$. I would like to know what is the distribution of $\max_i N_i$ Is there some paper where this result is shown?

  • $\begingroup$ Given $n$ independent random variables $X_1, \ldots, X_n$, we have $$\verb/Prob/\left[\max\limits_{1 \le i \le n} X_i \le x\right] = \verb/Prob/\left[ X_1 \le x \land \cdots \land X_n \le x \right] = \prod_{i=1}^n \verb/Prob/[ X_i \le x ]$$ CDF of max is just product of individual CDFs. $\endgroup$ Nov 12 '16 at 11:42
  • $\begingroup$ Can't I write this product as a new normal distribution? $\endgroup$
    – Sam
    Nov 12 '16 at 11:50
  • $\begingroup$ You cannot, max of normal random variables is not normal distributed $\endgroup$ Nov 12 '16 at 11:57

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.