Gravetter and Wallnau (2013) define hypothesis test as “a statistical method that uses sample data to evaluate a hypothesis about a population” (p. 233). Researchers conduct null hypothesis test to “determine whether mean differences among groups in an experiment are greater than the differences that are expected simply because of error variation” (Shaughnessy, Zechmeister, & Zechmeister, 2012, p. 385).

Stating hypothesis is usually the first step in a hypothesis test. The null hypothesis (H0) is the assumption that the independent variable (IV) does not have any effect on the dependent variable (DV). To test a null hypothesis, a value of α, called the alpha level or the level of significance should be selected first. A common α value is .05 (5%). According to Shaughnessy, Zechmeister, and Zechmeister (2012), the level of significance determines outcomes that direct researchers to reject the null hypothesis. When the null hypothesis were true, the likelihood of occurrence for a statistically significant outcome should be very low, therefore the null hypothesis is rejected if the test score’s probability of occurrence is less than the alpha level.

The alternative hypothesis (H1) states that “there is a change, a difference, or a relationship for the general population” (Gravetter & Wallnau, 2013, p. 236). For an experiment, the alternative hypothesis assumes that changing independent variable will not influence the dependent variable. An alternative hypothesis is accepted when the test score falls into the critical region. Bordered by the alpha level, the critical region is on the tail of the distribution with “extreme sample values that are very unlikely (as defined by the alpha level) to be obtained if the null hypothesis is true” (Gravetter & Wallnau, 2013, p. 238). In a hypothesis testing, the null hypothesis and the alternative hypothesis are mutually exclusive, thus researchers must make a decision to accept one and reject the other based on the experimental data.

In summary, hypothesis testing uses sample data to generate inferences about the population. The null hypothesis assumes that the independent variable does not have any effect on the dependent variable; the alternative hypothesis assumes that changing independent variable does affect the dependent variable. A research must conclude only one of the hypotheses is true.

References

Gravetter, F. J. & Wallnau, L. B. (2013). Statistics for the behavioral sciences (9th ed.). Belmont, CA: Wadsworth.

Shaughnessy, J. J., Zechmeister, E. B., & Zechmeister, J. S.(2012). Research methods in psychology (9th ed.). New York, NY: McGraw-Hill.

## No comments:

## Post a Comment