{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Notes pg132-146

# Notes pg132-146 - 132 Re-cap for Confidence Interval for...

This preview shows pages 1–5. Sign up to view the full content.

Re-cap for Confidence Interval for the Mean (σ Known) A confidence interval is a range of values that has a pre- specified probability of including the true value of the parameter. Therefore, a confidence interval for the mean is a range of values that has a pre-specified probability of including the mean, µ. The formula for a confidence interval for the mean when σ is known is: x ± z α /2 σ / n . The value of α/2 z (sometimes written as just “z”) depends on the level of confidence. The higher the level of confidence, the larger the z-score. For example, an 80% confidence interval for the mean is: x 1.28 n σ ± , whereas a 95% confidence interval for μ is: x 1.96 n σ ± . You should know how to determine the value of α/2 z for the desired confidence level. Example : Genron Corp. would like to determine the mean length of life for the high-performance model of tires that it supplies to an American automobile manufacturer. Forty tires are randomly selected from the manufacturing process and subjected to accelerated life-testing. The mean from the sample is 33,127 miles. Assume that the standard deviation for the population of tires (that is, σ ) is 7,500 miles. a. Construct a 95% confidence interval for the true mean life of this model of tire. 132

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
b. Carefully interpret the interval that you constructed in part a. in the context of the problem. 133
Confidence Intervals for the Mean, μ , When σ is Unknown The t-distribution The t-distribution, rather than the z-distribution (the standard normal) is used when we would like to estimate μ, but the population standard deviation, σ , is also unknown. In this case, when we take a sample to estimate μ with x , we also estimate with s. The t-distribution looks a lot like the σ standard normal. The t and the z distributions become more similar as the sample size, n, gets larger. The formula for a confidence interval for the mean when μ and are both unknown is: σ α/2,n-1 x ± t s n Where: α/2,n-1 x -μ t = s n Two assumptions should be met when constructing a confidence interval for μ with a t-score. They are: 1. Random sampling 2. Sampling from a normal population (x’s are normal). As noted above, a t-distribution looks a lot like a normal distribution. However, when n is small, the tails of the t- distribution are much heavier than a normal distribution. As 134

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
n gets larger and larger, the t-distribution looks more and more like the standard normal distribution.
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 18

Notes pg132-146 - 132 Re-cap for Confidence Interval for...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online