|
·
SAMPLE MULTIPLE CHOICE - EXAM 5-7
It
is NOT intended to act as a complete review of the material.
Answers appear at the end of the questions.
·
There will
NOT be calculation problems on the exam.
Answers appear at the end
Practice exam
Also see Chapter Self-Tests in the Study Guide that came with statistics
text. A copy of the self-tests is also on reserve in Stevenson Library.
Chapters 5 - 7
1. Which of the following is an example of the use of inferential
statistics?
a. Reporting the average exam scores obtained by two classes taught by
different methods.
b. Graphing frequency distribution of exams scores.
c. Concluding that the two teaching methods resulted in a difference in
performance.
d. Using interval or ratio data.
2. True or False? In hypothesis testing we directly test the research
hypothesis?
a. True, because the research hypothesis is the researcher’s
hypothesis.
b. True, because that way the research hypothesis can be proved.
c. False, we test the null or comparison hypothesis because that is the
researcher’s prediction.
d. False, we test the null hypothesis because it is known and we can
determine the probability of a
research result against this comparison hypothesis. .
3. A researcher using a significance level of .05, decides to reject
the null. This means that:
a. There was a less than 5% chance that the study result would have
been this extreme if the null hypothesis was true.
b. There was a more than 5% chance that the study result would have
been this extreme if the null hypothesis was true.
c. There was a 95% chance that the researcher made a Type I error.
d. There was a 95% chance that the researcher made a Type II error.
4. A researcher fails to reject the null. This also means that
a. The results were statistically significant.
b. The results were not statistically significant
c. The research hypothesis was supported.
d. A Type II error was definitely made.
5, A researcher is investigating the effects of a new instrument panel
in airplanes that is designed to help pilots more quickly diagnose
problems in aircraft engines.
The
research hypothesis is:
a. There will be no change in how quickly pilots diagnose engine
problems
b. Pilots will take more time to diagnose engine problems.
c. Pilots will take less time to diagnose engine problems.
d. Pilots will be more likely to make smooth landings.
6. The reseach hypothesis in item 5 is:
a. two-tailed
b. non-tailed
c. nondirectional
d. directional
7. The null hypothesis from item 5 would be:
a. There will be a change in how quickly pilots diagnose engine
problems.
b. Pilots will take the same or more time to diagnose engine problems.
c. Pilots will take the same or less time to diagnose engine problems.
d. Pilots will make more rough landings.
8. The cutoff value of a z-distribution is -/+2.58. A sample mean has
a z-score of -2.45. In hypothesis testing what would be one’s
conclusion?
a. The null would be rejected.
b. The research hypothesis would be supported.
c. The results would be inconclusive.
d. The null would have been rejected, if the z-score (-2.45) had been
positive.
9. You know some students taking Applied Research Methods and they
declare that their study proved their hypothesis. As a person with
superior understanding of hypothesis testing in psychology what do you
tell them?
a. Congratulations, you must have used a significance level of .01.
b. Congratulations, you found a significant result using a one-tailed
test.
c. Oops, you just made a Type II error.
d. Well, I’m glad you found support for your research hypothesis, but
you can’t say it’s “proven”.
10. A researcher believes that cognitive-behavioral therapy will reduce
depressive symptoms. How would the research be represented in symbolic
terms?
a. 
b. 
c. 
d.
11. The null hypothesis from item 10 would be represented in symbolic
terms by:
a. 
b. 
c. 
d.
12. A researcher conducts a paired-samples t-test. Are the results
significant?
|
Paired Samples Test |
|
|
Paired Differences |
|
|
|
Mean |
Std. Deviation |
Std. Error Mean |
t |
df |
Sig. (2-tailed) |
|
|
|
|
|
|
|
|
Pre_treatment -
Post_treament |
1.400 |
.966 |
.306 |
4.583 |
9 |
.001 |
|
|
a. Yes,
because .001 < .05 |
c. Yes,
because the standard error is small |
|
b. No, because
the degrees of freedom (df) are
too small. |
d. No, because
4.58 > .05 |
13. The researcher in item 12 expected that the post-treatment mean
would be higher than the pre-treatment mean – and that’s what she
found. However, if the difference had been in the opposite direction
would the results be significant?
|
a. No, because
the effect was in the opposite direction. |
c. Yes,
because the significance test is two-tailed. |
|
b. No, because
the degrees of freedom (df) are
too small. |
d. No, because
the t would be negative (-4.58) |
14. A researcher reports that the 95% confidence interval for a sample
is 34 – 38. This means
|
a. the
researcher is 95% sure that the sample mean is the same as the
population mean. |
|
b. the
researcher is 95% sure that the population mean is between 34
and 38. |
|
c. the
researcher is 5% sure that the population mean is between 34 and
38 |
|
d. The
researcher is 95% sure that the sample is less spread out than
the population is. |
15. I take a large number of random samples of the same size from a
population of scores. I calculate the mean of each sample and then
graph a frequency distribution of those means. What do I have?
|
a. a sampling
distribution of means |
c. a sample
frequency distribution |
|
b. a normal
distribution of z-scores |
d. a big mess! |
16. What will be the mean of the frequency distribution of mean be
described in item 15?
|
a. It will be
smaller than the population mean |
c. It will be
mean of a sample |
|
b. It will
depend on the size of the samples. |
d. It will be
the same as the population mean |
17. Suppose there are two sampling distributions of means based on the
same population. The first has a mean of 100 and a standard error of
20. The second also has a mean of 100 and a standard error of 10. What
can you assume about the size of the samples that were used to generate
the distributions of means?
|
a. the samples
from the first (Mean = 100, SD = 20) are larger than the samples
from the second
(Mean = 100, SE = 10) |
|
b. the samples
from the second are larger than the samples from the 1st.
|
|
c. the sample
sizes are the same. |
|
d. the
question is irrelevant because sample size is unrelated to the
sampling distribution of the
mean. |
18. What does the Central Limit theorem tell us about the shape of a
distribution of means?
|
a. If sample
size is large (e.g., 100) the distribution of means will be
normal even if the population is
not normal. |
|
b. The
distribution of means will look like a minature version of the
population. So if the population is
skewed, so is the distribution of means. |
|
c. The
distribution of means will be normal only if the underlying
population is normal. |
|
d. The shape
of the distribution of means depends solely on how spread the
population is.
The larger
s
is, the farther from normal the distribution of means will be.
 |
19. A standardized measure of the extent to which populations do not
overlap is
|
a. effect size |
c. standard
deviation |
|
b. standard
error |
d. z-score |
20. A researcher finds an effect size of 0.20. According to Cohen this
indicates a
|
a. no effect |
c. a medium
effect |
|
b. a small
effect |
d. a large
effect |
21. Suppose a treatment has a large effect, but a study investigating
the treatment does not show significant results. This means the study
has:
|
a. high power |
c. low power |
|
b. a
one-tailed test |
d. a large
mean difference |
22. Using less diverse populations increases power because:
|
a. the mean
differences will be larger. |
|
b. there will
be more overlap between populations. |
|
c. the
standard deviation of the distribution f means will be larger,
thus there will be more overlap |
|
d. the
standard deviation of the distribution of means will be smaller,
thus there will be less overlap |
23. Which researcher will have a more powerful test
|
a. Researcher
A uses a significance level of .01 and a two-tailed test.
|
|
b. Researcher
B uses a significance level of .05 and a one-tailed test.
|
|
c. Researcher
C uses a significance level of .01 and a one-tailed test.
|
|
d. Researcher
D uses a significance level of .05 and a two-tailed test.
|
|
Answers
|
|
1. |
c |
|
2. |
d |
|
3. |
a |
|
4. |
b |
|
5 |
c. |
|
6. |
d. |
|
7. |
b |
|
8. |
c |
|
9. |
d |
|
10. |
b |
|
11. |
c |
|
12. |
a |
|
13. |
c |
|
14. |
b |
|
15. |
a |
|
16. |
d |
|
17. |
b |
|
18. |
a |
|
19. |
a |
|
20. |
b |
|
21. |
c |
|
22. |
d |
|
23. |
b |
|
