Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

Based on a random sample of 20 values from a normal distribution with mean $\mu$ and variance $\sigma^{2}$, it was calculated that $\bar{X}=8$ and $s=4$. Provide a $95\%$ confidence interval for the population mean.

I know that I have to find $\bigl[\bar{X}-E,\bar{X}+E\bigr]$ since the sample is normally distributed. I also know that $E=Z_{c}\cdot\dfrac{\sigma}{\sqrt{n}}$. But after this, I'm not really sure what to do.

share|improve this question
add comment

2 Answers 2

It looks as if the variance is not known: only the sample variance is known.

Since $20$ is a fairly small number, it is more appropriate to use Student's t-distribution.

share|improve this answer
add comment

If the random variable $X$ is normally distributed, then its sample mean $\overline{X}$ is normally distributed. The requirement that $n$ be sufficiently large is only needed for cases where the distribution of $X$ is arbitrary.

Then $T=\frac{\overline{X}-\mu}{s/\sqrt{n}}$ follows the Student distribution with $n-1$ degrees of freedom (http://mathworld.wolfram.com/Studentst-Distribution.html). Because you don't know $\sigma$, you cannot use the normal distribution for setting a random variable $Z =\frac{\overline{X}-\mu}{\sigma/\sqrt{n}}$ which would be normally distributed (and even if $n$ is small, the base random variable $X$'s distribution is normal, so if $\sigma$ was known, it would still work).

So instead of the z-table, you need to look up the t-table. One is given here: http://math.usask.ca/~oshaughn/Student.pdf.

Correspondingly, the formula for $E$ is slightly different from the one where a $Z$ follows a normal distribution. $E=t_{n-1,\alpha/2} \frac{s}{\sqrt{n}}$.

share|improve this answer
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.