PSYC 515
HOMEWORK: R SPSS W IEVIEW ORKSHEET NSTRUCTIONS
OVERVIEW
This worksheet is designed to assess your ability to perform, interpret, report, and graphically
represent the following statistical tests using SPSS and standard reporting conventions as
covered in this course: correlations, regression, independent samples tests, and correlated t
groups tests. These are standard tests in our field and are foundational to the more sophisticated t
research designs. Knowledge of these tests provide fundamental skills to critically evaluating and
producing research in one’s field.
INSTRUCTIONS
Be sure you have reviewed this module’s assigned readings and presentations before completing
this assignment. This includes using ensuring the homework is completed and submitted
according to the instructions, SPSS output and images are legible and relevant, and that basic
college level writing skills (e.g., grammar) are used in the write-ups. Answers should be placed
where indicated (e.g., “ANSWER”). Note: all questions must be attempted to be eligible for full
credit. Please note that for all problems in this course, the standard cut-off (alpha) for a test of
significance will be .05, and you always report the exact power unless SPSS output states p=.000
(you’d report <.001). Also, remember that we divide the -value in half when reporting one-p p
tailed tests with 1 – 2 groups. Also – remember to check your graphs! You often have to ADD the
y – axis title.
Submit the file as a WORD document (.doc or .docx). Make sure the filename of your
submission includes your full name, course and section.
oExample: SPSS1_JohnDoe_515B01
Scenario 1
A major university would like to improve its tarnished image following a large on-campus
scandal. Its marketing department develops a short television commercial and tests it on a
sample of = 10, the first ten students who entered a housing commons area who agreed to n
participate. Attitudes about the university are measured with a short questionnaire, both before
and after viewing the commercial. Attitudes were on a scale of 0 – 20, which higher numbers
reflecting better attitudes. Use the provided data to examine whether the commercial improved
the university’s image. The data are as follows:
Person X (before) X (after)
1 2
A 15 15
B 11 13
C 10 18
D 11 12
E 14 16
F 10 10
G 11 19
H 10 20
Page 1 of 10
PSYC 515
I 12 13
J 15 18
1. In this specific scenario, what is the independent variable? Is it between or within
subjects? How many levels does it have, and what are they?
ANSWER
The independent variable is the commercial variable that is being displayed. It is considered
within subjects because the same indivduals were tested before and afer watching the
commercial to determine the attitude scale. It contains two levels because it measures the
attitude before and after the TV commercial.
2. In this specific scenario, what is the dependent variable? What is its scale of
measurement (nominal, ordinal, or scale)?
ANSWERThe depedendent variable is the attitude scale being measured from 0 to 20 before
and after the TV commercial. The scale of measurement is scale.
3. Paste all relevant statistical output in the space provided below:
ANSWER
4. Create an appropriate graph in SPSS and paste it in the space provided below:
ANSWER
Page 2 of 10
PSYC 515
5. Present the results using APA format. This includes a full write-up to include a
complete statistical notation as shown in the weekly presentations. The write-up also
needs interpretation. If significant, state . If it is not significant, what does that how
mean in layman’s terms? Additional examples of APA results sections are also
available in the “Helpful Hints” document.
ANSWERTo test the hypothesis that the attitude before the commercial (M=11.90, SD= 2.025)
and the attitude after the TV commercial (M =15.40, SC= 3.340) improved after viewing the
TV commercial S dependent samples t-test was performed and it found a significant difference
between the attitude before the participants viewed the commercial from after they viewed the
commercial t (9) = -2.976, p < .05. So, the null hypothesis is rejects that the attitudes improved
anout the school’s image after viewing the TV commercial.
6. Do you think this experiment has more internal validity or external validity? Explain
your answer. (You may want to review chapters 9-10 in your Jackson e-book).
ANSWERThis specific test has more external validity because the participants that were used
within the study were generalized. They only used the first ten individuals that walked into
that housing common’s area which would specify that the students who were chosen were
ones that precisely lived in that housing area but there was no extra information about if they
attended the local college, what grade they were in, or their major. Without this specific
information, the assumption can be made that those ten people were random and could be a
possible manipulation to the study due to their lot to little affiliation with the commercial in
general.
Scenario 2
To measure whether test performance can be predicted based on one’s anxiety, a researcher
Page 3 of 10
PSYC 515
asked his students to come to the lab 15 minutes before they were to take an exam in his class.
The researcher measured the students' heart rates and then matched these scores with their
exam performance after they had taken the exam. Use the data below and SPSS to test whether
heart rate can predict test performance in the population.
Student Heart Rate Exam Score
A 76 78
B 81 68
C 60 88
D 65 80
E 80 90
F 66 68
G 82 60
H 71 95
I 66 84
J 75 75
K 80 62
L 76 51
Page 4 of 10
PSYC 515
M 77 63
N 79 71
7. In this specific scenario, what are the two variables of interest? Which is the IV and
which is the DV? What is the scale of measurement for each variable?
ANSWERThe two variables are heart rate and exam scores. The independent variable is the
heart rate where the exam scores are the dependent variable. The scale of measurement for
both variables could be interval, ratio, or scale measurement.
8. Relate to this specific scenario: What is the null hypothesis? What is the alternate /
research hypothesis? Which one do you statistically assess?
ANSWERNull: There is no difference and/or relationship between a person’s heart rate and
exam scores.
Alternate: There is a relationship between a person’s heart rate and predicted test scores.
The null hypothesis is the one where you can conduct illative statisctial test.
9. Paste all relevant statistical output in the space provided below:
ANSWER
10. Create an appropriate graph in SPSS and paste it in the space provided below:
ANSWER
Page 5 of 10
PSYC 515
11. Present the results using APA format. This includes a full write-up to include a
complete statistical notation as shown in the weekly presentations. The write-up also
needs interpretation. If significant, state . If it is not significant, what does that how
mean in layman’s terms? Additional examples of APA results sections are also
available in the “Helpful Hints” document.
ANSWERA Pearson’s r correlation was used in this study to examine if there is a relationship
between the heart rate and exam scores. No relationship was found r (12) = -.481, p= .082 (two
tailed). The null hypothesis is retained; there is no relationship.
12. What is a potential confound of this study? Provide a sufficient justification.
ANSWERThe researcher asked the students to come in fifteen minutes early to have their
heart rates recorded. This could potintieally cause the students to be anxious causing their
heart rates to be abnormally high giving false readings based on the anticipation. If the
researcher wanted to more reasonable heart rates, he could have monitored the students heart
rates right before and right after the test seeing if the duration of time causes the readings to
change.
Scenario 3
A psychology instructor at a large university teaches statistics. There are 22 students in the
class, and he has broken them into two groups. Each group has a different graduate assistant
who is responsible for running separate breakout lecture and lab sections of the course. One
Page 6 of 10
PSYC 515
graduate assistant (GA) has lots of experience teaching, while the other has more limited
experience. The instructor wants to check for comparable learning across the two GAs, hoping
students receive similar experiences (i.e., to find no difference). The data below are the scores
(out of 100) of the students on the first midterm. Use it to test whether there is a difference
between the groups.
Group 1 (less
experienced GA)
Group 2 (more
experienced GA)
60 70
65 85
69 72
58 83
57 81
59 69
52 65
72 75
70 79
65 71
75 80
Page 7 of 10
PSYC 515
13. In this specific scenario, what is the independent variable? Is it between or within
subjects? How many levels does it have, and what are they?
ANSWER
The independent variable is group one with the less experienced GA and group two with the
mor experienced GA.
This is between subjects. The two levels are the two groups nominal.
14. In this specific scenario, what is the dependent variable? What is its scale of
measurement?
ANSWERThe dependent variable is the midterm scores. Its scale of measurement is scale.
15. Paste all relevant statistical output in the space provided below:
ANSWER
16. Create an appropriate graph in SPSS and paste it in the space provided below:
ANSWER
Page 8 of 10
PSYC 515
17. Present the results using APA format. This includes a full write-up to include a
complete statistical notation as shown in the weekly presentations. The write-up also
needs interpretation. If significant, state . If it is not significant, what does that how
mean in layman’s terms? Additional examples of APA results sections are also
available in the “Helpful Hints” document.
ANSWERA correlated t-test was conducted to compare a learning assessment on students
using two graduate assistants with two different experience levels; one has more experience
(group two) than the other (group one). The study showed that there was not a statistically
significant difference t (10) - -4.822, p<.001 r =.72% CI [-6.26, -17.013]. Therefore we fail to
2
reject the null hypothesis. We cannot say that ther is a statistically significant difference in the
groups exams from a graduate assistant who has more experience than a graduate assistant
who has less experience.
18. Using information from this scenario, determine the degrees of freedom and whether
this is a one- or two-tailed test. Use the Appendix in your e-book to find the critical
value. Do not round – provide the exact critical value below. Label it “critical value”.
Also provide the “obtained value” from your SPSS (and label it as such).
Compare the critical and obtained values – does the critical value exceed the obtained
value? What does this mean in regards to the null hypothesis (would you reject or fail
to reject the null hypothesis)?
ANSWERThe degree of freedom is 20. This test is a two tailed test because we are looking for
a difference in the relationship to occur. The critical value is 3.850. If you went off the paried
sampled t test df, that would equal 4.587, with a df=10. The obtained values is -4.822. This
would mean that you fail to reject the null hypothesis.
Note: This assignment will be checked for originality using the Turnitin plagiarism tool.
Page 9 of 10
