QUESTION: Based on a recent review of the literature, the researcher now has rea
ID: 3264753 • Letter: Q
Question
QUESTION: Based on a recent review of the literature, the researcher now has reason to believe the number of children is a possible confounding variable in the relationship between life satisfaction and current family income. Since the number of children is part of this data set, the researcher can use number of children as a covariant in an ANCOVA and mediate its impact as a possible confounding variable. Provide a narrative discussion of the table, including effect size, the results of the Levene test, and the observed change in the F-value of current family income when the number of children(childneg) was used as a co-variant. DATA BELOW:
Tests of Between-Subjects Effects
Dependent Variable: life satisfaction
Source
Type III Sum of Squares
df
Mean Square
F
Sig.
Partial Eta Squared
Corrected Model
19.410a
7
2.773
3.748
.001
.106
Intercept
1262.539
1
1262.539
1706.424
.000
.885
childneg
.792
1
.792
1.070
.302
.005
income
19.130
6
3.188
4.309
.000
.105
Error
163.512
221
.740
Total
5492.225
229
Corrected Total
182.922
228
a. R Squared = .106 (Adjusted R Squared = .078)
Levene's Test of Equality of Error Variancesa
Dependent Variable: life satisfaction
F
df1
df2
Sig.
.614
6
222
.719
Tests the null hypothesis that the error variance of the dependent variable is equal across groups.
a. Design: Intercept + childneg + income
Tests of Between-Subjects Effects
Dependent Variable: life satisfaction
Source
Type III Sum of Squares
df
Mean Square
F
Sig.
Partial Eta Squared
Corrected Model
19.410a
7
2.773
3.748
.001
.106
Intercept
1262.539
1
1262.539
1706.424
.000
.885
childneg
.792
1
.792
1.070
.302
.005
income
19.130
6
3.188
4.309
.000
.105
Error
163.512
221
.740
Total
5492.225
229
Corrected Total
182.922
228
a. R Squared = .106 (Adjusted R Squared = .078)
Explanation / Answer
Levene’s test is not significant with p-value=0.719>0.05 so that assumption of equality of variances is satisfied. Covariate number of children does not significantly affect life satisfaction, F(1,221 )=1.07, p=0.302>0.05 and explain only 0.5% variations in life satisfaction. After controlling for number of children, income has significant impact on life satisfaction, F(6,221)=4.31,p=0.000<0.05 and income explain 10.5% variations in life satisfaction.