Module 11: Confidence Intervals Part 1 This module roughly corresponds to chapter 8 in the textbook. Confidence intervals are a very common feature of polling. For a real world example, below is an excerpt from a September 15, 2015 article in Rasmussen Reports, a polling firm: 59% Think Hillary Likely To Have Broken The Law Most voters think Hillary Clinton needs to do a better job of explaining her use of a private e-mail server when she was secretary of State and suspect that she broke the law. Fifty-nine percent (59%) of Likely U.S. Voters think it’s likely Clinton broke the law by sending and receiving e-mails containing classified information through a private e-mail server while serving as secretary of State. A new Rasmussen Reports national telephone survey finds that just 34% believe Clinton is unlikely to have done anything illegal. This includes 42% who say it is Very Likely Clinton broke the law and only 15% who think it’s Not At All Likely. (To see survey question wording, click here .) Even among her fellow Democrats, 37% think it’s likely Clinton broke the law while using the private e-mail server at the State Department, with 16% who say it’s Very Likely […] The survey of 1,000 Likely Voters was conducted on September 10 and 13, 2015 by Rasmussen Reports. The margin of sampling error is +/- 3 percentage points with a 95% level of confidence. Field work for all Rasmussen Reports surveys is conducted by Pulse Opinion Research, LLC . See methodology . I’ve highlighted the key parts for this class in red. Rasmussen has effectively created a confidence interval. What this means is that we’re 95% confident that between 56 and 62% of likely U.S. voters believe Hillary broke the law with her email activities. We know this because the point estimate is 59% with a margin of error of +/- 3% and a 95% level of confidence. This is what this module and the next, Module, 12, will focus on.
Module 11: Confidence Intervals Part 1 In Module 11, we’ll focus on: A. Creating confidence intervals to estimate the population mean with large samples (n 30). B. Creating confidence intervals to estimate the population mean with large samples (n 30). In Module 12, we’ll focus on : A. Creating confidence intervals to estimate the population proportion. B. Creating confidence intervals to estimate the population variance. There are two components to a confidence interval: 1. The Point Estimate 2. The Confidence Interval Half Width •
Module 11: Confidence Intervals Part 1 1. The Point Estimate: The point estimate is the sample statistic for the population parameter you're estimating. For example: The point estimate for the population mean ( ) is the sample mean ( ) . The point estimate for the population variance ( 2 ) is the sample variance (s 2 ). The point estimate for the population standard deviation ( )is the sample standard deviation (s).