**Chapter 10**

- When is a significance test done using z? When is it done using t? What
is different about tests of differences between proportions?

- The scores of a random sample of 8 students on a physics test are given
below. Test to see if the sample mean is significantly different from 65 at
the .05 level.

60

62

67

69

70

72

75

80

- A (hypothetical) experiment is conducted on the effect of alcohol on perceptual
motor ability. Ten subjects are each tested twice, once after having two drinks
and once after having two glasses of water. The two tests were on two different
days to give the alcohol a chance to wear off. Half of the subjects were given
alcohol first and half were given water first. The scores of the 10 subjects
are shown below. The first number for each subject is their performance in
the "water" condition. Higher scores reflect better performance.
Test to see if alcohol had a significant effect. Use the .01 significance.

16 13

15 13

11 12

20 16

19 16

14 11

13 10

15 15

14 9

16 16

- 100 subjects are tested on three tasks. The experimenter wants to know whether
the correlation between tasks one and two is significantly different from
the correlation between tasks two and three. Why can't the method for testing
differences in correlations covered in this chapter be used?

- The scores on a (hypothetical) vocabulary test of a group of 20 year olds
and a group of 60 year olds are shown below. Test the difference for significance
using the .05 level.

**20 yr olds****60 yr olds**27

26

21

24

15

18

17

12

1326

29

29

29

27

15

20

27

- An experiment conducted by Michael Murphy-Corb and his associates tested
a new vaccine against aids in monkeys. Of the nine monkeys receiving the vaccine,
only one was infected. Of the 17 monkeys who received no vaccine, all 17 were
infected. Test the difference in proportions for significance using the .01
level.

- An experiment by John Rush and his associates compared the effectiveness
of cognitive therapy with the effectiveness of drug therapy for treating depression.
Of the 19 subjects in the cognitive therapy group, 15 recovered completely.
Of the 25 subjects in the drug therapy condition, only 5 recovered completely.
Test the difference for significance using the .05 level.

- A person claims to be able to throw a die and make a 1 come up more often
than chance (1/6). The die is thrown 100 times and a one comes up 18 times.
Is this proportion significantly different from 1/6?

- In a hypothetical experiment, the pain relief offered by heroin, morphine,
and a placebo are compared. Pain relief is rated on a 10 point scale where
higher numbers mean more pain relief. The results are shown below. Test whether
the average of the two drug conditions is significantly different from the
control group. Also test whether the two drug groups differ from each other.
Use the .05 level.

HeroinMorphinePlacebo9

9

8

9

10

9

88

7

8

9

8

7

83

4

3

5

4

2

4

- Test to see if the correlation between performance in the two experimental
conditions described in Question 3 is significant. Use the .05 level.

- A hypothetical experiment found that the correlation between height and
salary among male employees was .55 whereas it was only .11 among female employees.
There were 75 males and 81 females tested. Is the difference in correlations
significant at the .05 level?

- The standard deviation on a particular IQ test is known to be 15. A sample of 100 subjects was taken and the median was computed to be 107. Test to see if the median is significantly different from 100.