GROUP 1 SPSS WORKSHEET TWO-WAY ANOVA FINDINGS
Group 1: SPSS Worksheet 3 Two-Way ANOVA Findings
by
Rachel N. Hernandez
Tanea Robinson
Candi Skinner
Shontae Graham
Liberty University
Partial Fulfillment
Of the Requirements for EDUC 812
Liberty University
2018
GROUP 1 SPSS WORKSHEET TWO-WAY ANOVA FINDINGS
1
FINDINGS
Research Questions
The research in this study focused on answering the following questions:
RQ1: Is there a significant difference in the amount of time fathers play with their children
when they have no disability, a physical disability, or mental retardation?
RQ2: Is there a significant difference in the amount of time fathers play with their male or
female children?
RQ3: Is there a significant interaction among the amount of time fathers play with their male or
female children with no disability, a physical disability, or mental retardation?
Null Hypotheses
The researchers developed the following null hypotheses for this study:
H01: There is no significant difference among the amount of time fathers play with their children
with no disability, a physical disability, or mental retardation.
H02: There is no significant difference between the amount of time fathers play with their male
or female children.
H03: There is no significant interaction among the amount of time fathers play with their male or
female children with no disability, a physical disability, or mental retardation.
GROUP 1 SPSS WORKSHEET TWO-WAY ANOVA FINDINGS
2
Descriptive Statistics
Descriptive data obtained for the dependent variable amount of time playing for male and
female children who are either typically developing, physically disabled, or have mental
retardation can be found in Table 1. From this data set, one can infer from the mean score that
the amount of time spent playing with typically developing male and female children is greater
than the time spent playing with children who have a physical disability or mental retardation.
Additionally, the mean score for time spent playing with children who have a physical disability
or mental retardation is similar for both male and female children in all categories. While it is
always best practice to have similar sample populations, it is sometimes impossible to align these
group sizes. For the purpose of this study, the group sizes are close in size, therefore allowing
the examiner to make assumptions about the data between the groups.
Table 1
Descriptive Statistics
Group M SD N
Typical Male (TM) 7.30 1.83 10
Typical Female (TF) 6.80 2.20 10
Physical Male (PM) 3.00 1.56 10
Physical Female (PF) 3.40 1.90 10
Mental Male (MM) 3.22 1.72 9
Mental Female (MF) 4.00 1.61 11
GROUP 1 SPSS WORKSHEET TWO-WAY ANOVA FINDINGS
3
Results
Data screening
Data screening was conducted on each group’s (TM, TF, PM, PF, MM, MF) dependent
variable (amount of time playing) regarding data inconsistencies and outliers. The researchers
sorted the data on each variable and scanned for inconsistencies. Results indicate that all
variables were normally distributed. No data errors or inconsistencies were identified. Box and
whiskers plots were used to detect outliers on each dependent variable. No outliers were
identified. See Figure 1 for box and whisker plot.
Figure 1. Box and Whisker Plot for Disability Status of Child and Amount of Father’s Play.
GROUP 1 SPSS WORKSHEET TWO-WAY ANOVA FINDINGS
4
Assumptions
A Two-Way Analysis of Variance (ANOVA) was conducted to test the null hypothesis
that looked at the differences in the amount of time fathers play with their female or male
children with typical development, physical disabilities, or mental retardation. The Two-Way
ANOVA required that the assumptions of normality and homogeneity of variance are met. This
was completed using a Kolmogorov-Smirnov test. Kolmogorov-Smirnov was utilized due to the
sample size being 60 (more than 50). There were no violations of normality found within this
data. See Table 2 for Kolmogorov-Smirnov test.
Table 2.
Tests of Normality
Group Kolmogorov-Smirnov
Statistic df Significance
Typical Male (TM) .16 10 .20*
Typical Female (TF) .24 10 .10
Physical Male (PM) .16 10 .20*
Physical Female (PF) .22 10 .17
Mental Male (MM) .18 9 .20*
Mental Female (MF) .19 11 .20*
GROUP 1 SPSS WORKSHEET TWO-WAY ANOVA FINDINGS
5
Levene’s test was conducted to examine the assumption of homogeneity of variance. No
violation was found (p = .83) so the assumption of homogeneity was met. However, the Two-
Way ANOVA is considered a robust test against the homogeneity assumption (Warner, 2013, p.
474). For this reason, the researcher continued with the analysis. See Table 3 for Levene’s Test.
Table 3.
Levene’s Test of Equality of Error Variance
F df1df2 Significance
.43 5 54 .83
Results
A Two-way ANOVA was conducted to compare the main effects of interaction of fathers
with their male or female children with no disability, a physical disability, or an intellectual
disability on the amount of time fathers play with children. Disability type included three levels
(no disability, a physical disability, or mental retardation) and gender consisted of two levels
(male, female). All effects were statistically significant at the .05 significance level except for the
gender factor. The main effect for disability type yielded an F ratio of F(2, 54) = 27.14, p < .001,
indicating a significant difference between Typical (M = 7.05, SD = 1.99), Physical (M = 3.20,
SD = 1.700) and Mental (M = 3.65, SD = 1.66). The main effect for gender yielded an F ratio of
F(1, 54) = .232, p > .05, indicating that the effect for gender was not significant, male (M = 4.55,
SD = 2.61) and female (M = 4.71, SD = 2.37). The interaction effect was not significant, F(2, 54)
= .653, p > .001.
For the first null hypothesis (H01), the Partial Eta Squared value was 0.501, which
resulted in an extremely large effect size. The F-statistic (27.14) was greater than the F-critical
GROUP 1 SPSS WORKSHEET TWO-WAY ANOVA FINDINGS
6
value (3.17) and the p-value (<0.001) was less than 0.05. The researcher rejected the null
hypothesis, where F(2,54) = 3.17, p = <0.001. Since the null hypothesis was rejected and the
effect size was extremely large, a post hoc analysis was conducted to compare the mean
differences between disability categories. The results of the post hoc showed significant
differences between the typically developing vs physical disability groups and the typically
developing vs mental retardation groups.
For the second null hypothesis (H02), the Partial Eta Squared value was 0.004, which
resulted in a small effect size. The F-statistic (0.23) was less than the F-critical value (4.02), and
the p-value (0.004) was less than 0.05. The researcher failed to reject the null hypothesis, where
F(1, 54) = 4.02, p = 0.004. Since the researcher failed to reject the null hypothesis and the effect
size was small, a post hoc analysis was not conducted to compare the mean differences between
gender groups.
For the third null hypothesis (H03), the Partial Eta Squared value was 0.024, which
resulted in a medium effect size. The F-statistic (0.65) was less than the F-critical value (3.17),
and the p-value (0.53) was greater than 0.05. The researcher failed to reject the null hypothesis,
where F(2, 54) = 3.17, p = 0.53. Since the researcher failed to reject the null hypothesis and the
effect size was medium, a post hoc analysis was not conducted to compare the mean differences
between gender groups. See Table 4 for the Tests of Between-Subjects Effects.
GROUP 1 SPSS WORKSHEET TWO-WAY ANOVA FINDINGS
7
Table 4.
Tests of Between-Subjects Effects
Type III df Mean F Sig. Partial Eta
Sum of Square Squared
Squares
Disable 178.58 2 89.29 27.14 .00 .501
Gender .76 1 .76 .23 .63 .004
Disable * 4.29 2 2.15 .65 .53 .024
Gender
Error 177.66 54 3.29
Total 1648.00 60
Powered by TCPDF (www.tcpdf.org)
