21.01.2022 Views

Statistics for the Behavioral Sciences by Frederick J. Gravetter, Larry B. Wallnau ISBN 10: 1305504917 ISBN 13: 9781305504912

Statistics is one of the most practical and essential courses that you will take, and a primary goal of this popular text is to make the task of learning statistics as simple as possible. Straightforward instruction, built-in learning aids, and real-world examples have made STATISTICS FOR THE BEHAVIORAL SCIENCES, 10th Edition the text selected most often by instructors for their students in the behavioral and social sciences. The authors provide a conceptual context that makes it easier to learn formulas and procedures, explaining why procedures were developed and when they should be used. This text will also instill the basic principles of objectivity and logic that are essential for science and valuable in everyday life, making it a useful reference long after you complete the course.

Statistics is one of the most practical and essential courses that you will take, and a primary goal of this popular text is to make the task of learning statistics as simple as possible. Straightforward instruction, built-in learning aids, and real-world examples have made STATISTICS FOR THE BEHAVIORAL SCIENCES, 10th Edition the text selected most often by instructors for their students in the behavioral and social sciences. The authors provide a conceptual context that makes it easier to learn formulas and procedures, explaining why procedures were developed and when they should be used. This text will also instill the basic principles of objectivity and logic that are essential for science and valuable in everyday life, making it a useful reference long after you complete the course.

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

238 CHAPTER 8 | Introduction to Hypothesis Testing

Unlike a Type I error, it is impossible to determine a single, exact probability for a Type II

error. Instead, the probability of a Type II error depends on a variety of factors and therefore

is a function, rather than a specific number. Nonetheless, the probability of a Type II

error is represented by the symbol β, the Greek letter beta.

In summary, a hypothesis test always leads to one of two decisions.

1. The sample data provide sufficient evidence to reject the null hypothesis and conclude

that the treatment has an effect.

2. The sample data do not provide enough evidence to reject the null hypothesis. In

this case, you fail to reject H 0

and conclude that the treatment does not appear to

have an effect.

In either case, there is a chance that the data are misleading and the decision is wrong. The

complete set of decisions and outcomes is shown in Table 8.1. The risk of an error is especially

important in the case of a Type I error, which can lead to a false report. Fortunately,

the probability of a Type I error is determined by the alpha level, which is completely

under the control of the researcher. At the beginning of a hypothesis test, the researcher

states the hypotheses and selects the alpha level, which immediately determines the risk

of a Type I error.

TABLE 8.1

Possible outcomes of a

statistical decision.

Actual Situation

No Effect

H 0

True

Effect Exists,

H 0

False

Experimenter’s

Decision

Reject H 0

Type I error Decision correct

Fail to Reject H 0

Decision correct Type II error

■ Selecting an Alpha Level

As you have seen, the alpha level for a hypothesis test serves two very important functions.

First, alpha helps determine the boundaries for the critical region by defining the concept

of “very unlikely” outcomes. At the same time, alpha determines the probability of a Type I

error. When you select a value for alpha at the beginning of a hypothesis test, your decision

influences both of these functions.

The primary concern when selecting an alpha level is to minimize the risk of a Type

I error. Thus, alpha levels tend to be very small probability values. By convention, the

largest permissible value is α = .05. When there is no treatment effect, an alpha level of

.05 means that there is still a 5% risk, or a 1-in-20 probability, of rejecting the null hypothesis

and committing a Type I error. Because the consequences of a Type I error can be relatively

serious, many individual researchers and many scientific publications prefer to use

a more conservative alpha level such as .01 or .001 to reduce the risk that a false report is

published and becomes part of the scientific literature. (For more information on the origins

of the .05 level of significance, see the excellent short article by Cowles and Davis, 1982.)

At this point, it may appear that the best strategy for selecting an alpha level is to choose

the smallest possible value to minimize the risk of a Type I error. However, there is a different

kind of risk that develops as the alpha level is lowered. Specifically, a lower alpha level

means less risk of a Type I error, but it also means that the hypothesis test demands more

evidence from the research results.

The trade-off between the risk of a Type I error and the demands of the test is controlled

by the boundaries of the critical region. For the hypothesis test to conclude that the

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!