QUANTITATIVE RESEARCH METHODS - ASSIGMENT 5
mother’s education and father’s education were ordered variables and ordinal data. Cramer’s V
(and phi) was compared to Kendall’s tau-b. The
Results
show that to investigate the relationship
between the father’s and mother’s education, Kendall’s tau-b was conducted. The analysis indi
cated a statistically significant positive association between father’s and mother’s education, tau
(71) = .572. p < .001. This means that more highly educated fathers were married to more highly
educated mothers and less educated fathers were married to less educated mothers. This tau is
considered a large effect size (Morgan et al., 2013).
A5.4: Chapter 8, Problem 8.4, Cross‐Tabulation and Eta
A5.4.a. Narrative of the Process
An important associational statistic, eta, is used when one variable is nominal and the
other is approximately normal or scale. I will use this statistic to describe the association between
gender and math courses taken.
Crosstabs
Table 11: Case Processing Summary
Table 12: Math courses taken * Gender Crosstabulation
8
02/16/2020

QUANTITATIVE RESEARCH METHODS - ASSIGMENT 5
Table 13: Directional Measures
A5.4.b. Interpretation of the Findings
The interpretation indicates that
the second table shows the actual Counts and the
Expected Counts of the number of persons in each cell. When there are positive discrepancies
between the actual and expected counts in the upper left (male) columns and negative
discrepancies in the lower left columns or vice versa, it indicates that there is an association be
tween the two variables. Because of the way the SPSS program computes eta, it ranges from zero
to about +1.0. High values of eta indicate a strong association. For this problem, the appropriate
eta is .328 because math courses taken is the dependent variable. It is a medium to large effect
size. With 75 subjects, an eta of .33 probably would be statistically enough, but this program
does not test it. Eta squared would be .11, indicating that the two variables share 11% common
variance. You will see eta squared when interpreting the size of the “effect” in analysis of
variance.
Eta was used to investigate the strength of the association between gender and number
of math courses taken (eta = .33). This is a medium to large effect size. Males were more likely
to take several or all math courses than females (Morgan et al., 2013).
A5.5, Application Problem ‐ Crosstabulation and Chi‐Square
A5.5a Output 1:
Gender and Martial Status
A5.5.a.1. Narrative of the Process
The process to follow for this problem is to open SPSS, then Analyze-Descriptive
Statistics-Crosstabs. After that, move gender into Rows box and marital into Columns box. Click
9
02/16/2020

QUANTITATIVE RESEARCH METHODS - ASSIGMENT 5
on Statistics and check Chi-square, Phi and Cramer’s V, and click continue. In the cross-tab