Suppose you took a sample of n=20 observations, and your sample was: {56, 58, 50, 51, 65, 74, 71, 77, 76, 88, 95, 93, 100, 93, 91, 94, 93, 92, 94, 96} We would like to construct a 95% Confidence Interval for the mean, using this data. Unfortunately, we do not know the population standard devi- ation (we only have sample data), so we can’t use the Normal. We also can’t use the Normal since our sample size is small. And since the parent population doesn’t seem to be Normal, we can’t use the “t.” What do we do? Calculate 20k re-samples of size n=20 from the sample above. For each resample, calculate and store the mean. Use the empirical dis- tribution of these 20k means to construct a i. 90% Confidence Interval ii. 95% Confidence Interval iii. 99% Confidence Interval
Suppose you took a sample of n=20 observations, and your sample was:
{56, 58, 50, 51, 65, 74, 71, 77, 76, 88, 95, 93, 100, 93, 91, 94, 93, 92, 94, 96}
We would like to construct a 95% Confidence Interval for the mean, using this data. Unfortunately, we do not know the population standard devi- ation (we only have sample data), so we can’t use the Normal. We also can’t use the Normal since our
-
Calculate 20k re-samples of size n=20 from the sample above. For each resample, calculate and store the mean. Use the empirical dis- tribution of these 20k means to construct a
i. 90% Confidence Interval ii. 95% Confidence Interval iii. 99% Confidence Interval
Trending now
This is a popular solution!
Step by step
Solved in 2 steps
