STA 215 INTRODUCTION TO STATISTICAL REASONING NOTES Reading: Sections 1-4 on pages 334-385. Chapter 8: Statistical Inference: Confidence Intervals Why do we use sample data to learn about population data? Recall from previous chapters that researchers are often interested in learning about a population. Unfortunately, collecting data from every element in a population can be difficult. Instead, researchers will take a subgroup from the population, known as the sample, to examine. Definitions: Population: The population is who/what we want to learn about or examine. Most of the time it is a large group but does not have to be. Sample: The sample is the set of individuals, items, or animals selected from the population. Once the sample is selected, we can collect and analyze data. Parameter: The parameter is the specific piece of information we would like to learn about that population. If we cannot collect data from the entire population, then we will not know the value of the parameter. Statistic: The statistic is an estimate of the piece of information we would like to know about the population but calculated from the sample. It is our best guess for the parameter. In this chapter, we are going to continue to develop a set of tools that will allow us to take the information contained in the sample to say something reasonable about what is occurring the population. Previously in Chapter 7, we studied the behavior of the statistic and to see what the behavior of the statistic suggests about the parameter. We saw that if we create a sampling distribution that the statistics follow a bell-shaped pattern. We will review the sampling distribution. What does the sampling distribution tell us about the behavior of statistics? First, let's review what a sampling distribution is