Question

As you move on from this course to PSY 301: Research Methods, there are two skills that will be critical to your success: (1) the ability to choose the appropriate statistical test for a given research study and (2) the ability to communicate the results of a statistical test clearly, concisely, and completely. Your textbook has two great resources to help with both of these: Appendix E and Appendix F. Review these appendices before completing Question Sets 3 and 4.

A. An academic adviser wants to know if the mean score on a new academic readiness measure is greater than 80 points for all Ecampus students. Scores on the academic readiness measure are interval-level. They give the survey to a representative sample of 50 Ecampus students. What statistical test should they use to address their research question? Explain why.

B. Researchers are replicating Albert Bandura’s famous Bobo Doll Experiment. They have three groups of children: the first group is exposed to adults showing aggressive behaviors towards Bobo, the second group is exposed to adults playing with Bobo non-aggressively, and the third group is a control that is not exposed to anything. Aggressive behaviors are measured using an interval-level scale after the intervention. What statistical test should they use to determine if there is evidence that the mean aggressive behaviors scores are different between the three groups? Explain why.

C. A statistics instructor wants to know if there is a positive relationship between their students’ scores on a measure of statistics anxiety and their final grades in the course. Both statistics anxiety and final course grades were measured quantitatively (i.e., interval-/ratio-level). What statistical test should they use to address their research question? Explain why.

Answer 1

A. An academic adviser wants to know if the mean score on a new academic readiness measure is greater than 80 points for all Ecampus students. Scores on the academic readiness measure are interval-level. They give the survey to a representative sample of 50 Ecampus students.

Answer: One tail One proportion Z test should be used to test this research this question. The z test can be used when the sample size is over 30 and is generally used to test the claim whether the mean scores of a group vary with their population means.

B. Researchers are replicating Albert Bandura’s famous Bobo Doll Experiment. They have three groups of children: the first group is exposed to adults showing aggressive behaviors towards Bobo, the second group is exposed to adults playing with Bobo non-aggressively, and the third group is a control that is not exposed to anything. Aggressive behaviors are measured using an interval-level scale after the intervention.

Answer: ANOVA test should be used to compare the means of 3 groups. Generally, the ANOVA test is used when mean scores need to be compared for 3 or more groups. It can tell if there is any difference in the mean scores of the three groups.

C. A statistics instructor wants to know if there is a positive relationship between their students’ scores on a measure of statistics anxiety and their final grades in the course. Both statistics anxiety and final course grades were measured quantitatively (i.e., interval-/ratio-level).

Answer: Pearson's correlation test can be used to determine the relationship between the student's scores on a measure of statistics anxiety and their final grades in the course.