Recall that \( \boldsymbol{X}_{1}, \ldots, \boldsymbol{X}_{n} \) are i.i.d. standard normal variables. Denote by \( A_{n} \) the sample mean of the squares of these variables:
\[
A_{n}:=\overline{X_{n}^{2}}=\frac{1}{n} \sum_{i=1}^{n} X_{i}^{2}=\frac{1}{n}\left(X_{1}^{2}+X_{2}^{2}+\ldots+X_{n}^{2}\right) .
\]
\( 2(e) \)
20 points possible (graded, results hidden)
Recal \( A_{a}=\frac{1}{n} \sum_{i=1}^{n} X_{i}^{2} \). Use the CLT and the fact that qo.o5 \( \left(A_{1}\right)=3.84 \) to approximate the 0.95 -quantile qo.05 \( \left(A_{m}\right) \) of the random variable \( A_{n} \) for sample sizes \( n=100 \) and \( n=10^{6} \).
(Recall the \( 1-\alpha \) quantile \( q_{a}(Y) \) of a variable \( Y \) is defined by \( P\left(Y>q_{a}(Y)\right)=\alpha \) )
(Enter an answer accurate to at least 3 decimal places.)
\( 90.05\left(A_{100}\right)= \) \( \square \)
\( 9005\left(A_{10}\right)= \) \( \square \)