1. Srinivasulu Rajendran
Centre for the Study of Regional Development (CSRD)
Jawaharlal Nehru University (JNU)
New Delhi
India
r.srinivasulu@gmail.com
2. Objective of the session
To understand two-way
anova through software
packages
3. 1. What is the procedure to
perform Two-way ANOVA?
2. How do we interpret results?
4. Two-way ANOVA using SPSS
The two-way ANOVA compares the mean differences
between groups that have been split on two
independent variables (called factors). You need two
independent, categorical variables and one
continuous, dependent variable .
5. Objective
We are interested in whether an monthly per capita
food expenditure was influenced by their level of
education and their gender head. Monthly per capita
food expenditure with higher value meaning a better
off. The researcher then divided the participants by
gender head of HHs i.e Male head & Female head HHs
and then again by level of education.
6. In SPSS we separated the HHs into their appropriate
groups by using two columns representing the two
independent variables and labelled them “Head_Sex"
and “Head_Edu". For “head_sex", we coded males as
"1" and females as “0", and for “Head_Edu", we coded
illiterate as "1", can sign only as "2" and can read only as
"3“ and can read & write as “4”. Monthly per capita food
expenditure was entered under the variable name,
“pcmfx".
7. How to correctly enter your data into SPSS in order to
run a two-way ANOVA
8. Testing of Assumptions
In SPSS, homogeneity of variances is tested using
Levene's Test for Equality of Variances. This is
included in the main procedure for running the two-
way ANOVA, so we get to evaluate whether there is
homogeneity of variances at the same time as we get
the results from the two-way ANOVA.
14. You need to transfer the dependent variable “pcmfx"
into the "Dependent Variable:" box and transfer both
independent variables, “head_sex" and “head_edu", into
the "Fixed Factor(s)”
18. Transfer the
independent
variable
“head_edu" from
the "Factors:" box
into the
"Horizontal Axis:"
box and transfer
the “head_sex"
variable into the
"Separate Lines:"
box. You will be
presented with the
following screen:
[Tip: Put the
independent
variable with the
greater number of
levels in the
"Horizontal Axis:"
box.]
20. Click the “add”
button
You will see that
“head_edu*head
_sex" has been
added to the
"Plots:" box.
Click the
“continue”
button. This will
return you to the
"Univariate"
dialogue box.
22. Click the “Post Hoc..” button. You will be presented with the
"Univariate: Post Hoc Multiple Comparisons for Observed..."
dialogue box as shown below:
24. Transfer “head_edu" from the "Factor(s):" box to the
"Post Hoc Tests for:" box. This will make the "Equal
Variances Assumed" section become active (loose the
"grey sheen") and present you with some choices for
which post-hoc test to use. For this example, we are going
to select "Tukey", which is a good, all-round post-hoc test.
[You only need to transfer independent variables that
have more than two levels into the "Post Hoc Tests for:"
box. This is why we do not transfer “head_sex".]
You will finish up with the following screen
Click the “Continue” button to return to the "Univariate"
dialogue box
27. Click the “option” button. This will present you with the
"Univariate: Options" dialogue box as shown below:
Transfer “head_sex", “head_edu" and “head_sex*head_edu"
from the "Factor(s) and "Factor Interactions:" box into the
"Display Means for:" box. In the "Display" section, tick the
"Descriptive Statistics" and "Homogeneity tests" options. You
will presented with the following screen
Click the “continue” button to return to the "Univariate"
dialogue box.
32. SPSS produces many tables in its output from a two-way
ANOVA and we are going to start with the "Descriptives"
table as shown below:
Descriptive Statistics
Dependent Variable:Per capita monthly food expenditure (taka)
Head of the
Household - Sex (sum) head_edu Mean Std. Deviation N
Male 1 939.8895 455.16118 245
2 998.0697 491.73339 262
3 858.3107 383.20545 20
4 1137.9562 534.76858 571
Total 1055.2881 512.60856 1098
Female 1 962.6195 627.75916 44
2 967.0070 424.26461 41
4 1205.5084 607.04529 52
Total 1056.1239 574.00781 137
Total 1 943.3501 484.17553 289
2 993.8665 482.62690 303
3 858.3107 383.20545 20
4 1143.5946 540.95653 623
Total 1055.3809 519.52636 1235
33. This table is very useful as it provides
the mean and standard deviation for
the groups that have been split by
both independent variables. In
addition, the table also provides
"Total" rows, which allows means
and standard deviations for groups
only split by one independent
variable or none at all to be known.
34. From this table we can
Levene's Test of Equality of Error Variancesa
see that we don’t have
homogeneity of
variances of the
dependent variable Dependent Variable:Per capita monthly food expenditure
across groups. We (taka)
know this as the Sig.
value is less than 0.05, F df1 df2 Sig.
2.335 6 1228 .030
which is the level we
set for alpha. So we
have concluded that
the variance across
Tests the null hypothesis that the error variance of the
groups was dependent variable is equal across groups.
significantly different a. Design: Intercept + head_sex + head_edu +
(unequal). head_sex * head_edu
35. Tests of Between-Subjects Effects Table
The table shows the actual results of the two-way ANOVA as
shown
We are interested in the head of hhs gender, education and
head_sex*head_edu rows of the table as highlighted above.
These rows inform us of whether we have significant mean
differences between our groups for our two independent
variables, head_sex and head_edu, and for their interaction,
head_sex*head_edu. We must first look at the
head_sex*head_edu interaction as this is the most important
result we are after. We can see from the Sig. column that we have
a statistically NOT significant interaction at the P = .686 level.
You may wish to report the results ofhead_sex and head_edu as
well. We can see from the above table that there was no
significant difference in monthly per capita food exp between
head_sex (P = .675) but there were significant differences
between educational levels (P < .000).
36. Tests of Between-Subjects Effects
Dependent Variable:Per capita monthly food expenditure (taka)
Type III Sum of
Source Squares df Mean Square F Sig.
Corrected Model 10669432 6 1778239 6.773 .000
Intercept 279013110 1 279013110 1062.753 .000
head_sex 46145 1 46145 .176 .675
head_edu 5527869 3 1842623 7.019 .000
head_sex * 197900 2 98950 .377 .686
head_edu
Error 322396593 1228 262538
Total 1708644528 1235
Corrected Total 333066026 1234