Chapter Introduction

179

6

Introduction to Hypothesis Testing

LEARNING OBJECTIVES

  • Explain how hypothesis testing works.

  • List the six steps to be followed in completing a hypothesis test.

  • Explain and complete a single-sample z test.

  • Explain the decisions that can be made in hypothesis testing.

CHAPTER OVERVIEW

This chapter makes the transition from descriptive statistics to inferential statistics. In inferential statistics, specific information from a sample is used to draw a general conclusion about a population. For example, this allows a researcher to study one group of people with depression and to draw a conclusion that applies to people with depression in general. This transition to inferential statistics starts with the logic that statisticians use to reach decisions, a process called hypothesis testing.

After this prelude, the chapter takes a pragmatic turn with coverage of the single-sample z test, which we’ll use to demonstrate how hypothesis testing works. Psychology researchers rely on statistics to help them make thoughtful, data-driven decisions. The single-sample z test allows researchers to determine if a sample mean is statistically significantly different from a population mean or some other specified value.

Completing a hypothesis test is a lot like baking. Before you can put the cake in the oven, you must go to the store to buy the ingredients, turn on the oven, measure out the ingredients, and mix them together in the right order. This chapter introduces a six-step procedure that can be used for all hypothesis tests to make sure that the right steps happen in the right order. We even offer a mnemonic—Tom and Harry despise crabby infants—to keep everything straight.

The chapter ends with an exploration of the different types of correct and incorrect conclusions that can occur. The incorrect conclusions have names: Type I error and Type II error. For a single-sample z test, a Type I error occurs when one erroneously concludes that a sample mean differs from a population mean. Type II error is the opposite—it occurs when the researcher indicates there is no evidence that the sample mean differs from the population mean and the sample really does differ.

6.1 The Logic of Hypothesis Testing

6.2 Hypothesis Testing in Action

6.3 Type I Error, Type II Error, Beta, and Power