- BYU Home
- FHSS
- Psychology
- Psychology 301
- Chapter 13
Chapter 13 Questions
Complete the following questions. The questions may include pictures or graphics to illustrate or aid in solving the problem. You can check your answer by clicking View Answer. If the question is unclear, confusing, or if you need further clarification, send me an email.
1. T-test activity.
Answer
See activity.---Please note that on the independent measures activity the second mean should equal 55 not 50 as notated.
2. Given the data below, imagine that the scores on an extroversion scale were obtained before and then after subjects were trained in effective communication skills. Does the communication skills training significantly affect extroversion scores?
Answer
Looking the critical t on the t-table under two tails, 5 degrees of freedom, .05 level, critical t = 2.571. We reject the null hypothesis and conclude that communication skills training does make a difference to measures of extroversion.
3. Given the data below from question two in chapter fourteen, imagine now that the scores on the empathy scale actually were obtained before and then after subjects received sensitivity training and that we hypothesized that the training would improve scores. Is our hypothesis correct?
Before After
81 86
79 84
77 83
77 83
75 82
73 80
Answer
Looking the critical t up on the t-table under one tail, 5 degrees of freedom, .05 level, critical t = 2.015. We reject the null hypothesis and conclude that sensitivity training does improve empathy ratings.
4. Compare your t-values obtained in your present analyses with the values you obtained for questions one and two in chapter fourteen. How do the results differ? Why is the dependent samples t-test considered to be an error-reducing test?
Answer
The t-values for the present chapter are both greater than those of chapter fourteen. This is because the dependent measures t-test looks at differences between scores which are assumed to be correlated with one another (on the basis of matching or repeated measures). Because some of the variation among scores can be accounted for on the basis of the correlation between the two sets of data, the unexplained variation, or error, is reduced, yielding a greater t-value.