MHB Confidence Interval for Mean $\mu$: Let $X_1, X_2, \dots, X_n$

AI Thread Summary
The discussion focuses on deriving a confidence interval for the mean $\mu$ based on a random sample with known expected value and variance. It establishes that for any value of $k$ within the range [0,1], the specified interval formula provides a 100(1-a)% confidence interval for $\mu$. Participants seek clarification on the meaning of $k$ and the notation $z_{k=a}$. The conversation emphasizes understanding the statistical concepts involved in constructing confidence intervals. Overall, the thread aims to clarify the parameters and methodology for confidence interval calculation.
evinda
Gold Member
MHB
Messages
3,741
Reaction score
0
Hello! (Wave)

Let $X_1, X_2, \dots, X_n$ a random sample with $E(X_i)=\mu$, $Var(X_i)=\sigma^2 \forall i$. For $0<a<0.5$:

show that for any $k \in [0,1]$, the interval
$$\left( \overline{X}-z_{k=a} \frac{\sigma}{\sqrt{n}}, \overline{X}+z_{(1-k)=a} \frac{\sigma}{\sqrt{n}}\right)$$
is a 100(1-a)% confidence interval for the mean $\mu$.

How could we do this? (Thinking)
 
Physics news on Phys.org
evinda said:
Hello! (Wave)

Let $X_1, X_2, \dots, X_n$ a random sample with $E(X_i)=\mu$, $Var(X_i)=\sigma^2 \forall i$. For $0<a<0.5$:

show that for any $k \in [0,1]$, the interval
$$\left( \overline{X}-z_{k=a} \frac{\sigma}{\sqrt{n}}, \overline{X}+z_{(1-k)=a} \frac{\sigma}{\sqrt{n}}\right)$$
is a 100(1-a)% confidence interval for the mean $\mu$.

How could we do this? (Thinking)

Hey! (Smile)

What is $k$? And what is $z_{k=a}$? (Wondering)
 
Back
Top