SPSS ASSIGNMENT #2
Creating Scatter Diagrams and More
Review and follow the steps in your text and you may want to keep SPSS Statistics 21 Brief Guide handy just
in case.
1a.
The following have been prepared so that data sets B through D are slightly modified versions of data set
A. Make scatter diagrams and figure the correlation coefficients for each data set.
DATA SET A
X
Y
1
1
2
2
3
3
4
4
5
5
1b.
DATA SET B
X
Y
1
1
2
2
3
3
4
5
5
4
DATA SET C
X
Y
1
5
2
4
3
3
4
2
5
1
DATA SET D
X
Y
1
1
2
4
3
3
4
2
5
5
Discuss how and why the correlations change.
Correlations
Review the steps in your text and you may want to keep SPSS Statistics 21 Brief Guide handy just in case.
2.
Enter the following data into SPSS. Determine the correlation between hours of studying and grade point
average in these honor students. Copy and paste the results into this document. Explain your results.
Hours of Studying
23
12
15
14
16
21
14
11
18
9
Chi-Square
SPSS instructions:
Chi-Square Test for Goodness of Fit:
Open SPSS
GPA
3.95
3.90
4.00
3.76
3.97
3.89
3.66
3.91
3.80
3.89
Remember that SPSS assumes that all the scores in a row are from the same participant. In the study presented in #1,
there are 20 students, some of whom have been suspended for misbehavior. The primary conflict-resolution style
used by each student is also entered. [Ignore the first variable in this analysis.]
When you have entered the data for all 20 students, move to the Variable View window and change the first variable
name to SUSPEND and the second to STYLE. Set the number of decimals for both variables to zero.
Click Analyze Non-Parametric Tests Chi-Square
Click the variable STYLE and then the arrow next to the box labeled Test Variable List to indicate that the chisquare for goodness of fit should be conducted on the conflict-resolution style variable.
Note that All categories equal is the default selection in the Expected Values box, which means that SPSS will
conduct the goodness of fit test using equal expected frequencies for each of the four styles, in other words, SPSS
will assume that the proportions of students each style are equal.
Click OK.
Chi-Square Test for Independence:
Open SPSS
For #2, you need to add the variable SUSPEND to the analysis. Remember that in this problem, we are interested
in whether there was an association between conflict-resolution style and having been suspended from school for
misbehavior. Since the analysis will involve two nominal variables, the appropriate test is a chi-square test for
independence.
Click Analyze Descriptive Statistics Crosstabs
Since SUSPEND is already selected, click the arrow next to the box labeled Rows.
Click the variable STYLE and click the arrow next to the box labeled Columns.
Click Statistics and click the box labeled Chi-Square.
Click Continue.
Click Cells and click the box labeled Expected.
Click Continue.
Click OK.
1.
The following table includes the primary method of conflict resolution used by 20 students.
Method
N of Students
Aggressive
8
Manipulative
2
Passive
2
Assertive
8
a.
b.
2.
Following the five steps of hypothesis testing, conduct the appropriate chi-square test to determine
whether the observed frequencies are significantly different from the frequencies expected by change
at the .05 level of significance. Clearly identify each of the five steps.
Explain your response to some who has never had a course in statistics.
Next, researchers categorized the students based on the primary method of conflict resolution used and
whether the student had been suspended from school for misbehavior. These data are presented below.
Suspended
Yes
No
Total
Aggressive
7
1
8
Method
Manipulative
Passive
1
1
1
1
2
2
Assertive
1
7
8
Total
10
10
20
a.
Following the five steps of hypothesis testing, conduct the appropriate chi-square test to determine
whether the observed frequencies are significantly different from the frequencies expected by change
at the .05 level of significance. Clearly identify each of the five steps.
b.
Calculate the effect size.
c.
Explain your response to someone who has never had a course in statistics.
Computing z-Scores Using SPSS
Using the data below:
1.
Determine the z-score that corresponds to each teachers salary and enter them in the table below.
(Follow the steps on the second page).
The following data are from a survey of high school teachers.
SALARY
SEX
35,000
Male
18,000
Female
20,000
Male
50,000
Female
38,000
Male
20,000
Female
75,000
Male
40,000
Female
30,000
Male
22,000
Female
23,000
Male
45,000
ZSALARY
Female
Follow the instructions below. For salary be sure to use scale for measure (and you will be entering the actual
number so no need for values); sex is a nominal variable (Male= 1, Female=2).
In SPSS, we compute z-scores via the Descriptives command.
After you enter the data above, click Analyze, then Descriptive Statistics, then Descriptives this will take you to
the dialog box for descriptives.
In the bottom-left corner you will see a check box labeled Save standardized values as variables, check this box
and move the variable SALARY into the right-hand blank. Then click OK to complete the analysis. You will see the
standard output from the Descriptives command. Notice that the z-scores are not listed. SPSS inserts them into the
data window as a new variable (ZSALARY). Copy and paste your results to this document.
2.
Write a brief (but thorough) analysis of what these z-scores say about each teachers salary.
Crosstabs
For this assignment you will be using the data contained in the following file (you can find it under Resources)
soci332_dataset.sav
The Crosstabs command produces frequency distributions for multiple variables. This command is useful for
describing samples where the man is not useful (that is, nominal or ordinal scales) and as a method for getting a feel
for your data.
To run crosstabs:
Click Analyze, then Descriptive Statistics, then Crosstabs. A dialog box will appear with your variables on the
left-hand side and a Row(s) box, Column(s) box, and Layer 1 of 1 box. Move the variable SEX to the Row(s) box,
and the ANY OTHER VARIABLE YOU WANT (or use another attitude-variable that interests you) to the
Columns(s) box. [If you wanted to analyze more than two variables, you would enter the third, fourth, fifth, etc., in
the Layer 1 of 1 box].
Click on the Cells button in the bottom of the dialog box. This button allows you to specify percentages and other
information that you would like from each combination of values. Once you click on Cells, another dialog box
appears, select Observed under Counts; Row, Column, Total under Percentages then click on Continue. You will
return to the Crosstabs dialog box, where you will click OK.
Assignment:
1.
Your assignment is to run at least 5 crosstabs, copy and paste them to this document and briefly explain
each of them.
Single Sample & Dependent Samples t Tests
SPSS instructions: (For more details, check the links provided under Course Materials in the Course
Overview Folder (under Lessons).
t Test for a Single Sample:
Open SPSS
Enter the number of activities of daily living performed by the depressed clients studied in #1 in the Data View
window.
In the Variable View window, change the variable name to ADL and set the decimals to zero.
Click Analyze Compare Means One-Sample T test the arrow to move ADL to the Variable(s) window.
Enter the population mean (14) in the Test Value box.
Click OK.
t Test for Dependent Means:
Open SPSS
Enter the number of activities of daily living performed by the depressed clients studied in Problem 2 in the Data
View window. Be sure to enter the before therapy scores in the first column and the after therapy scores in the
second column.
In the Variable View window, change the variable name for the first variable to ADLPRE and the variable name
for the second variable to ADLPOST. Set the decimals for both variables to zero.
Click Analyze Compare Means Paired-Samples T Test the arrow to move ADLPRE to the Paired
Variable(s) window ADLPOST and then click the arrow to move the variable to the Paired Variable(s)
window.
Click OK.
Review the five steps of hypothesis testing and complete the following problems. Be sure to cut and past the
appropriate result boxes from SPSS under each problem.
1.
Researches are interested in whether depressed people undergoing group therapy will perform a different
number of activities of daily living after group therapy. The researchers have randomly selected 12
depressed clients to undergo a 6-week group therapy program.
Use the five steps of hypothesis testing to determine whether the average number of activities of daily
living (shown below) obtained after therapy is significantly different from a mean number of activities of
14 that is typical for depressed people. (Clearly indicate each step).
Test the difference at the .05 level of significance and, for practice, at the .01 level (in SPSS this means you
change the confidence level from 95% to 99%).
In Step 2, show all calculations.
As part of Step 5, indicate whether the behavioral scientists should recommend group therapy for all
depressed people based on evaluation of the null hypothesis at both levels of significance and calculate the
effect size.
CLIENT
A
B
C
D
E
F
G
H
I
J
K
L
2.
AFTER THERAPY
17
15
12
21
16
18
17
14
13
15
12
19
Researchers are interested in whether depressed people undergoing group therapy will perform a different
number of activities of daily living before and after group therapy. The researchers have randomly selected
8 depressed clients in a 6-week group therapy program.
Use the five steps of hypothesis testing to determine whether the observed differences in numbers of
activities of daily living (shown below) obtained before and after therapy are statistically significant at the .
05 level of significance and, for practice, at the .01 level. (Clearly indicate each step).
In Step 2, show all calculations. As part of Step 5, indicate whether the researchers should recommend
group therapy for all depressed people based on evaluation of the null hypothesis at both levels of
significance and calculate the effect size.
CLIENT
A
B
C
D
E
F
G
H
BEFORE THERAPY
12
7
10
13
9
8
14
11
AFTER THERAPY
17
15
12
21
16
18
17
8
The t Test for Independent Samples
SPSS instructions to run the t Test for Independent Samples: (For more details, check the links provided
under Course Materials in the Course Overview Folder (under Lessons).
Once you have entered the data, click on Analyze, then on Compare Means, and then click on IndependentSamples T Test
A dialog box will appear, with your variables (student, condition, score) on the left. Your options are (a) move one
or more variables into the Test Variable(s) box to select your dependent variables(s) and (b) move one of your
variables into the Grouping Variable box to select the independent variables (or identify the groups to be
compared).
Make ? the dependent variable by moving it to the Test Variable(s) box. Then make ? your independent
variable by moving it to the Grouping Variable box. Now, the Define Groups button is functioning, click on
Define Groups and another dialog box appears. Here you must specify the two values of the condition variable that
represent the two groups you are comparing. Click in the box next to Group 1 and type the number 1, then click in
the box next to Group 2 and type the number 2. Now you can click Continue to return to the Independent-Samples
T Test dialog box, and click on OK to run the analysis.
1.
Six months after an industrial accident, a researcher has been asked to compare the job satisfaction of
employees who participated in counseling sessions with the satisfaction of employees who chose not to
participate.
The scores on a job satisfaction inventory for both groups are listed in the table below.
Use the five steps of hypothesis testing to determine whether the job satisfaction scores of the group that
participated in counseling are statistically higher than the scores of employees who did not participate in
counseling at the .01 level of significance.
In Step 2, show all calculations.
As part of Step 5, indicate whether the researcher should recommend counseling as a method to improve
job satisfaction following industrial accidents based on evaluation of the null hypothesis and calculate the
effect size.
PARTICIPATED IN COUNSELING
36
39
40
36
38
35
37
39
42
2.
DID NOT PARTICIPATE IN COUNSELING
37
35
36
33
30
38
39
35
32
A researcher is interest in the effect of exercise on the perceptions of well-being among older. The
researcher identified 30 residents of a retirement community and divided them into groups of 15 residents.
Both groups were encouraged to walk at least 20 minutes per day. One group, however, also participated in
a structured exercise program that emphasized flexibility. After 6 weeks, the behavioral scientist mailed
questionnaires to the 30 residents. Responses to an item asking residents to rate their perceptions of their
health on a 10-point scale on which 1 indicated very unhealthy and 10 indicated very healthy are
presented in the table that follows.
Use the five steps of hypothesis testing to determine whether the observed differences in health ratings of
the two groups are statistically significant at the .05 level of significance.
In Step 2, show all calculations.
As part of Step 5, indicate whether the researcher should recommend exercise as a method to improve
perceptions of health among older adults based on evaluation of the null hypothesis and calculate the effect
size.
WALKING AND FLEXIBILITY
5
6
6
4
9
4
7
9
6
7
9
7
4
9
8
Analysis of Variance
SPSS instructions:
Open SPSS
WALKING ONLY
2
3
4
3
6
7
7
6
7
4
6
Analyze the data for #1. Remember that SPSS assumes that all the scores in a row are from the same participant. In
this study, there are 15 participants divided into three groups of five. Therefore, each of the 15 participants will be
described by two variables, type of therapy and the number of activities of daily living performed.
If 1 represents the group receiving individual therapy for 1 hour every 2 weeks, 2 represents the group receiving
1 hour of individual therapy each week, and 3 indicates the group receiving 2 hours of individual therapy each
week, the first participant will be described by entering 1 in the top cell of the first column in the Data View
window and 16 in the top cell of the second column to indicate that the participant underwent 1 hour of therapy
every 2 weeks and performed 16 activities of daily living. The second participant will be described by 1 and 15,
and the third by 1 and 18.
When the two variables have been entered for the five participants in this group, repeat the process for participants
who underwent 1 hour of individual therapy each week, using 2 to describe their therapy group. When the two
variables for the five participants in this group have been entered, repeat the process for Group 3, entering 3 in the
first column. In the Variable View window, change the first variable name to THERAPY and the second to
ADL and set the decimals for both to zero.
Click Analyze Compare Means One-Way ANOVA Since THERAPY is already selected, you can click
the arrow to move the variable to the Factor window. Select ADL and click the arrow to move the variable to the
Dependent List window, which instruct SPSS to conduct the analysis of variance on the number of activities
performed.
1.
Keep in mind that the clients in Group 1 will receive 1 hour of therapy every 2 weeks, the clients in Group
2 will receive 1 hour of therapy every week, and the clients in Group 3 will receive 2 hours of therapy
every week.
Use the five steps of hypothesis testing to determine whether the observed differences in the number of
activities in the following table performed by the three groups are statistically significant at the .05 level of
significance. Clearly indicate each of the five steps.
Calculate the effect size for the study. Explain your results.
CLIENT
1
2
3
4
5
2.
GROUP 1
16
15
18
21
19
GROUP 2
21
20
17
23
19
GROUP 3
24
21
25
20
22
A researcher interested in the relationship between student perception of the probability of success in a
statistics course and student motivation has administered an inventory designed to assess motivation in 18
students.
The students have been divided into groups as follows: Students in Group 1 believe they are highly likely
to succeed in the course, students in Group 2 believe they have an intermediate probability of success, and
students in Group 3 believe they have little chance of success.
Use the five steps of hypothesis testing to determine whether the observed differences in level of
motivation in the following table are statistically significant at the .05 level of significance. Clearly indicate
each of the five steps.
Calculate the effect size for the study. Explain the results of the hypothesis-testing procedure to someone
who is familiar with the t test for independent means, but not with analysis of variance.
SUBJECT
1
2
3
4
5
6
3.
GROUP 1 (HIGH)
9.0
8.5
6.5
7.0
8.0
5.5
GROUP 2 (INTERMEDIATE)
3.5
5.5
6.5
3.5
4.5
7.0
GROUP 3 (LOW)
4.5
5.5
6.5
8.0
5.5
6.0
Due to the increasing number of trails involving testimony by behavioral scientists, a professional
organization of behavior scientists asked judges, attorneys, jurors, and law enforcement officials to use a
10-point scale to rate the effect of such testimony on trial outcomes.
The results are presented in the table below. Use the five steps of hypothesis testing to determine whether
the observed differences in effectiveness ratings are statistically significant at the .01 level of significance.
Clearly indicate each of the five steps.
Calculate the effect size for the study. Explain your results.
CATEGORY
Judges
Attorneys
Jurors
Law Enforcement
N
6
6
6
6
M
7.00
5.83
7.83
3.00
S2
1.99
1.37
1.37
3.61