- BYU Home
- FHSS
- Psychology
- Psychology 301
- Chapter 15
Chapter 15 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. Define the concept of statistical power.
Answer
Power: The ability of our statistical tests to accurately identify statistical differences in our data. It is the sensitivity to differences of our statistical analyses.
2. What are the three methods for increasing statistical power?
Answer
1) Increase the alpha level. 2) Increase mean differences. 3) Increase the sample size.
3. What does your instructor mean by "post hoc" and "a priori" approaches to power?
Answer
Post hoc approach: Statistical power may be calculated after a significant difference is found to determine how effective the treatment was or the degree to which the results may generalize. A priori approach: Researchers may be interested in designing a study in such a way as to increase the likelihood of finding significant differences. The power formula allows the researcher to identify the number of subjects he or she will need to achieve a particular power.
4. Given that the population mean IQ is 100 and the standard deviation is 15, what is the power associated with the single-sample t-test of the following data:
X
121
119
118
118
117
115
Answer
5. How many persons would we have to sample to obtain a likelihood of finding a significant difference of .90?
Answer
6. Now, imagine that the sample from question four was compared to another set of IQ scores from a different group of participants, such that we have the data below. What would be the power associated with the independent samples t-test comparing the two samples?
X Y
121 108
119 106
118 102
118 105
117 104
115
105
Answer
7. Now, imagine the same data as in questions four. However, this time assume the same group of participants completed an IQ test on two different occasions. What would the power be in this case?
Answer
8. Is statistical power a concept with which researchers ought to be concerned?
Answer
- Answers will vary.