Question

Dr. Snooze looked at the effect of sleep deprivation on cognitive functioning in elderly men and women. He contacted local doctors specializing in geriatrics to obtain a sample for this study. On Monday morning at 8:00 am after 8 hours of sleep the night before, and then again a week later at 8:00 am after 4 hours of sleep the night before, 35 subjects solved a complicated maze when they arrived at the lab in the morning and the time to complete the maze was recorded for each subject.

A. To increase power of the study, Dr. Snooze would _____________.

1. give subjects an easier maze to solve

2. calculate each subject’s z score

3. conduct both a one-tailed test and a two-tailed test and use the less lenient result

4. select subjects from a more diverse population

5. use a .05 significance level (alpha) instead of .01

6. all of the above are correct

B. The study _____________, so Dr. Snooze should _______________.

1. has a large sample size; conduct a z-test

2. has a small sample size; sample from a more diverse population

3. 2x2 factorial design; 2-way ANOV A

4. uses a within-subjects design; conduct a dependent-samples t-test

5. uses correlational design; conduct a Pearson r

6. uses a between-subjects design; One-way ANOV A

Answer 1

A:

As the level of significance increases type II error decreases. As the type II error decreases power of the test increases.

So correct option is:

use a .05 significance level (alpha) instead of .01

B:

Here we have paired data because same subjects are used under two conditions

Correct option is:

uses a within-subjects design; conduct a dependent-samples t-test