0
$\begingroup$

Let $X$ be the outcome of a chance experiment with $E(X) = \mu$ and $V(X) = \sigma^2$. When $\mu$ and $\sigma^2$ can be estimated by repeating the experiment $n$ times with outcomes $x_1, x_2,...,x_n$, sample mean and variance are given by: $$\bar x = \frac{1}{n}\sum_{i=1}^{n}x_i$$ $$ s^2 = \frac{1}{n}\sum_{i=1}^{n}(x_i-\bar x)^2 $$

This is followed by problems asking to prove $E(\bar x)=\mu$, $E((\bar x-\mu)^2)=\sigma^2/n$, $E(s^s)=\frac{n-1}{n}\sigma^2$. My question is notation related, should I be looking at $x_1, x_2,...x_n$ and $\bar x$ as random variables (which are typically denoted by capital letters in my book) each with $\mu$, $\sigma^2$, not actual outcomes of a specific sample (lower case letters are typically used to represent values i.e. $P(X = x)$)? This is a bit ambiguous since from the equations for $\bar x$ and $s^2$ I think (?) it could be interpreted both ways but in the proof it doesn't make sense if we are looking at a specific sample.

$\endgroup$
  • 1
    $\begingroup$ May be relevant: math.stackexchange.com/questions/435846/… $\endgroup$ – NoChance May 21 at 0:33
  • 1
    $\begingroup$ I think you have to do exactly what you deduced in your question. For instance, it is trivial to see that if you do this the fact that $E(\bar{x})=\mu$ becomes immediate. $\endgroup$ – Ariel Serranoni May 21 at 0:34
1
$\begingroup$

Yes, the $x_i$ are independent random variables having the distribution of $X$. Thus $\overline{x}$, which is defined in terms of the $x_i$’s, is a random variable, and so is $s^2$.

$\endgroup$

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.