STAT 311 Study Guide - Final Guide: Confidence Interval, Normal Distribution, Point Estimation
Document Summary
A confidence interval communicates how accurate our estimate is likely to be. The width of a confidence interval depends on two things: variation within the population of interest and the sample size. If all the values in the population are nearly the same, our sample will have a small confidence interval. If there is more variation in the population we would have a wider confidence interval, so we would be less sure our interval is representative of the population. Small sample sizes will vary more from each other, so there is more variation. The effect of sampling error is reduced with larger samples. When we use the traditional normal-based way of figuring out confidence intervals, the stated level of confidence also affect the width of the confidence interval. It is a way to show what the uncertainty is with a certain statistic. For example, a poll might state that there s a 98% confidence interval of 4. 88 and 5. 26.