PSYC 515
SPSS HOMEWORK 8 INSTRUCTIONS: PUTTING IT ALL TOGETHER (40 POINTS)
When submitting this file, be sure the filename includes your full name, course, and section. Example:
HW8_JohnDoe_515B03
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 p<.001).
Also, remember that we divide the p-value in half when reporting one-tailed tests with 1 – 2 groups.
Dr. St. Peter’s Michelle Marshall-Harry 5/8/20
1) The p value we’ve used in PSYC 510 and 515 was
set at .05, but others in our field at times use .01. If
researchers used the same assessments and sample
sizes, lowering the alpha would affect what?
Answer:
The statistical significance
2) Several meta-analyses reveal that many published
research studies in our field suffer from low
statistical power, primarily due to what?
Answer:
An inadequate sample size
3) According to the “Final Considerations” presentation,
what term is the “probability of correctly rejecting
the null hypothesis”, and is typically set at 0.8?
Answer:
Power is the probability of making a correct
decision toreject the null hypothesis
4) By law, publishers own the copyright on their journal
articles for how many years from the time of
publication?
Answer: 95 years from the date of publication
5) According to APA conventions, the title should be no
more than how many words?
Answer: no more than 12 words
None for this week.
6) List one strength of a nonparametric test. (2 pts)
Answer: One strength of the nonparametric
tests is that they can be used without
making any assumptions about the form of
the underlying distributions.
7) If your goal is to not only explore a relationship between
two variables but also predict one given the value of the
other, which type of statistical test is most appropriate? (2
pts)
Answer: Regression analysis
8) What statistical test is most appropriate if you want to
examine whether there is a difference in graduation rates
(percentages) between home schooling, public schools, and
Answer: One-Way Randomized ANOVA
P 1 – CONCEPTS this ’s assigned and pres (2 = 10 )
P 2 – SPSS APPLICATION ’s readings presentations
P 3 – CUMULATIVE include theoretical, -calculations, and use SPSS any
cover thus f . (8+22 = 30 )
PSYC 515
Problem Set 1: (22 pts)
A teacher wanted to see if social anxiety affects performance on an oral assignment. To examine
this, students completed social anxiety scales and were classified into “low,” “average,” and “high”
levels of social anxiety. The data presented in the table below are the oral presentation grades (in
percentages) earned by the 45 students separated by their social anxiety classification. Conduct
the most appropriate statistical analysis to determine whether grades on the oral assignment
differed based on level of social anxiety. (Hint: see week 1 presentations)
private schools in your state of residence? Assume the data
meets the assumptions for a parametric test. (2 pts)
9) What statistical test would be most appropriate if you
measured religiosity (using an interval scale) every 5 years
for a total of 20 years in the same participants (so, four
data points per person), but the data did not meet the
assumptions for a parametric test?
Answer: One-Way Repeated ANOVA
Oral presentation grade (%)
Low
social anxiety
Average
social anxiety
High
social anxiety
72
80
77
68
85
71
73
73
73
75
81
69
97
73
90
73
91
74
95
73
76
88
73
67
89
71
81
97
75
75
88
78
68
89
90
79
93
89
58
89
88
83
79
75
81
10) What is the dependent variable and its scale of measurement in this scenario? (2 pts)
Performance on an oral assignment - Scale
11) State the independent variable in the scenario, its scale of measurement, and its number of levels. (3 pts)
Social anxiety – normal – three levels
PSYC 515
12) Paste appropriate SPSS output. (4 pts)
Test of Homogeneity of Variances
Levene
Statistic df1 df2 Sig.
Group Based on Mean 2.342 2 42 .109
Based on Median .829 2 42 .443
Based on Median
and with adjusted df
Based on trimmed
.829 2 35.216 .445
2.242 2 42 .119
mean
ANOVA
Group
Sum of
Squares
df
Mean
Square
F
Sig.
Between Groups 681.733
2
340.867
4.845
.013
Within Groups 2955.067
42
70.359
Total 3636.800
44
Multiple Comparisons
Dependent Variable: Group
(I) Anxiety
(J) Anxiety
Mean
Difference (I-
J)
Std. Error
Sig.
95% Confidence Interval
Lower Upper
Bound Bound
Tukey HSD
1
2
4.667
3.063
.290
-2.77
12.11
3
9.533*
3.063
.009
2.09
16.97
2
1
-4.667
3.063
.290
-12.11
2.77
3
4.867
3.063
.262
-2.57
12.31
3
1
-9.533*
3.063
.009
-16.97
-2.09
2
-4.867
3.063
.262
-12.31
2.57
LSD
1
2
4.667
3.063
.135
-1.51
10.85
3
9.533*
3.063
.003
3.35
15.71
2
1
-4.667
3.063
.135
-10.85
1.51
3
4.867
3.063
.120
-1.31
11.05
3
1
-9.533*
3.063
.003
-15.71
-3.35
2
-4.867
3.063
.120
-11.05
1.31
*. The mean difference is significant at the 0.05 level.
PSYC 515
13) Calculate and interpret the effect size. (3 pts)
n² =ssbetween/sstotal
n² =681.733/3636.800
n² =.1875 or 18.75%
14) Paste appropriate SPSS graph, formatted in APA (2 pts). Write an appropriate figure caption using APA
conventions. 2 pts for graph; 2 pts for caption = 4 pts total.
Figure 1. Mean grade performance (0-100) for students with low social anxiety(n=15), average social
Anxiety(n=15), and high social anxiety(n=15). Students with high anxiety showed significally lower scores
than low and average social anxiety(p=.013). Error bars represent standard deviations.
15) Write an APA-style Results section based on your analysis. All homework “Results sections” should follow
the examples provided in the presentations and textbooks. They should include the statistical statement
within a complete sentence that mentions the type of test conducted, whether the test was significant, and a
decision about each null hypothesis tested. Include effect sizes, post hoc analyses / interpretations, and refer
the reader to Figure(s) created above, when appropriate (4 pts).
A One-Way ANOVA was conducted to examine whether social anxiety ( low, average, and high)
influenced oral presentation scores. The null hypothesis is rejected – there is a difference in low, average
and high social anxiety on oral presentation score F(2,42)=4.845,p = .013.Tukey post hoc analysis revealed
that low social anxiety resulted in higher test scores than having average or high social anxiety. No other
PSYC 515
hoc comparisons were significant (p>.05). An eta- squared effect size indicated that.18.75 of the variance iv
the test performance was due to the condition to which a person was randomly assigned.
16) Identify a potential confounding variable with the study as it was presented (you can use your imagination!).
Justify why you think it may be a confounding rather than an extraneous variable. (2 pts)
The confounding variable within this study does not effect all groups.
DONE! S 11:59 . . (ET) FRIDAY M /W 8.
