4
$\begingroup$

There is a sample of n values that are the first n largest values of a population. Is there a way of getting any statistic such as mean or dispersion from such piece of information provided that the population is normally distributed with its size either known or unknown?

Improve this question
$\endgroup$
5
  • 1
    $\begingroup$ You can estimate the parameters of a normal from order statistics. Note that for the population to be normal, it must be infinite (and therefore really only notional). You could treat what you're calling the population as a random sample from the infinite population, and then you'd treat your largest $n$ values as the largest order statistics from that large sample. You would then estimate the $\mu$ and $\sigma$ of the underlying 'infinite' normal population. $\endgroup$
    – Glen_b
    Commented May 20, 2014 at 23:43
  • $\begingroup$ Thanks, now, from "and then you'd treat.." on. How to? $\endgroup$
    – Germaniawerks
    Commented May 21, 2014 at 10:14
  • $\begingroup$ You observe the n largest samples, but do you know how many samples q were drawn in the first place? Do you have a reasonable prior on the value of q? $\endgroup$
    – Giancarlo
    Commented May 21, 2014 at 15:34
  • 1
    $\begingroup$ I have n largest values from a sample of N values and I need to estimate the sample mean and deviation - or whatever statistic I can get. Sample size N may be either known or unknown. $\endgroup$
    – Germaniawerks
    Commented May 21, 2014 at 15:44
  • 1
    $\begingroup$ what's stopping you from taking an MLE approach? $\endgroup$
    – Dale C
    Commented Dec 19, 2019 at 5:56

0

Reset to default

Your Answer

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