PSY 555 Homework 12
Chapter 8: #1,3,7,8,9,15
8.1(b). The function of n for a one-sample t-test is equal to .
8.3(a). For power=.70,
Round up because you cannot have 99 participants.
So, you would need 99 participants to have a power of .70.
8.3(b). For power=.80,
So, you would need 126 participants to have a power of .80.
8.3(c). For power=.90,
So, you would need 169 participants to have a power of .90.
You would need 16 participants to have a power of .50.
8.7(b). For power=.80,
You would need 32 participants to achieve a power of .80.
8.8(a). For power=.60,
78 participants (39 in each group) would be needed to achieve a power of .60.
8.8(b). For power=.90,
170 participants (85 in each group) would be needed to achieve a power of .90.
The power of this experiment is .29.
8.15. High School Dropouts Delinquent Graduates
He should use the high school dropout group because that group will produce the highest power.
1. Alpha is the probability of rejecting the null hypothesis when the null hypothesis is true (the probability of making a Type I error). Beta is the probability of failing to reject the null hypothesis when the null hypothesis is false (the probability of a Type II error). Power is the probability of finding an effect given there is an effect to be found (e.g., rejecting the null hypothesis when you should have rejected the null hypothesis; defined as 1-b).
2. You can increase power by:
1) increasing sample size (N),
2) creating a larger effect size (by increasing the experimental manipulation—e.g., raise the drug dose of an experimental group to a higher level to compare to a control),
3) use a more sensitive statistical test,
4) adjust the alpha level (specifically, increase alpha level; e.g., .05 moves to .10), or
5) increasing the sensitivity of the measure (e.g., measure in inches rather than yards).