The null hypothesis is a hypothesis which states that there is “no effect, no difference, or no relationship among the variables being studied” (Smith, Gratz, & Bousquet, 2009, p. 161). Conversely, the alternative hypothesis is a hypothesis that claims that there is an effect, a relationship, or a difference between the studied variables. These two hypotheses are opposites (Smith et al., 2009).
The reason for employing both types of hypotheses is the precision of the study. For instance, the null hypothesis, which denies the relationship between the variables, is precise (and, as a precise universal statement, it is relatively simple to reject: it’s only needed to find a significant counterexample), whereas the alternative hypothesis, according to which there is some type of relationship, is imprecise.
Therefore, in studies, the alternative hypothesis is not proved or disproved; on the contrary, researchers either fail to reject the null hypothesis (and find no support for the alternative hypothesis) or reject the null hypothesis (and find evidence that supports the alternative hypothesis) (Gravetter & Wallnau, 2008; Smith et al., 2009).
Simon-Dack (2014) measured the difference in students’ performance on four tests taken before and after participating in a learning activity aimed at exploring the action potential. The four null hypotheses for the study state that there would be no difference in the students’ performance before and after the activity on the four tests. Each of the four alternative hypotheses states that there would be a difference on one of the four tests the students took.
The conclusions from this study are as follows: there is a significant difference between the performance on three of the four tests taken before and after the activity; these tests are multiple-choice questions, the assessment of one’s belief in one’s understanding of the subject, and the essay questions; p values are.002,.031, and.024, respectively. Therefore, these three null hypotheses were rejected, and the three alternative hypotheses were supported. However, there was no significant difference in the scores of the tests measuring the students’ belief about how well they can explain the materials; p =.103. Thus, the corresponding null hypothesis was not rejected.
References
Gravetter, F., & Wallnau, L. (2008). Essentials of statistics for the behavioral sciences (6th ed.). Belmont, CA: Thomson Wardsworth.
Simon-Dack, S. L. (2014). Introducing the action potential to psychology students. Teaching of Psychology, 41(1), 73-77. Web.
Smith, L. F., Gratz, Z. S., & Bousquet, S. G. (2009). The art and practice of statistics. Belmont, CA: Cengage Learning.