TWO WAY
ANOYA
(ANALYSIS OF
VARIANCE)
HADIA ARSHAD
0416-MPHIL-Z-21
ANOVA
Analysis of variance
Ronald Fisher in 1918
compare the means of more than two groups.
T-test 2 groups, sample size 30
ANOVA more than 2 groups, sample size not limited
ANOVA
Two types of variables
Dependent variable numeric, continuous
Independent variable categorical
Type of ANOVA, based on variation in these two variables;
One Way ANOVA one independent
Factorial ANOVA more than one independent Variable
Two Way ANOVA two independent variable
MANOVA two or more dependent variables
TWO-WAY ANOVA
Dependent variable one in number
Independent variable two in number
Purpose;
If there is any interaction between two independent variables on
dependent variable
E.g., whether there is an interaction between gender and
educational level on test anxiety amongst university students,
where gender (males/females) and education level
(undergraduate/postgraduate) are your independent variables,
and test anxiety is your dependent variable.
EFFECTS
The main effects term informs you whether the independent
variables influence the dependent variable separately.
For example, if the effect of gender on anxiety is statistically
significant or not. And if the effect of education on anxiety is
statistically significant or not.
The interaction effect term informs you whether the effect of one
of your independent variables on the dependent variable is the same
for all values of your other independent variable (and vice versa).
For example, is the effect of gender (male/female) on test anxiety
influenced by educational level (undergraduate/postgraduate)?
ASSUMPTION#1
• Your dependent variable should be measured at
the continuous level.
• Examples
• revision time (measured in hours),
• intelligence (measured using IQ score),
• exam performance (measured from 0 to 100),
• weight (measured in kg), and so forth.
ASSUMPTIONS#2
• Your two independent variables should each consist of two or
more categorical, independent groups.
• Example
• gender (2 groups: male or female)
• ethnicity (3 groups: Caucasian, African American and Hispanic)
• profession (5 groups: surgeon, doctor, nurse, dentist, therapist)
ASSUMPTIONS#3
Independence of observations, which means that there is no
relationship between the observations in each group or between the
groups themselves.
For example,
There must be different participants in each group with no participant
being in more than one group.
This is more of a study design issue than something you would test for,
but it is an important assumption of the two-way ANOVA. If your study
fails this assumption, you will need to use another statistical test
instead of the two-way ANOVA (e.g., a repeated measures design).
The assumption of independence can be determined from the design of
the study
ASSUMPTION#4
There should be no significant outliers.
Outliers are data points within your data that do not follow the usual
pattern.
For example;
In a study of 100 students' IQ scores, where the mean score was
108 with only a small variation between students, one student had a
score of 156, which is very unusual, and may even put her in the top
1% of IQ scores globally.
The problem with outliers is that they can have a negative effect on
the two-way ANOVA, reducing the accuracy of your results.
Fortunately, when using SPSS Statistics to run a two-way ANOVA on
your data, you can easily detect possible outliers.
ASSUMPTION #5
Your dependent variable should be approximately normally
distributed for each combination of the groups of the two
independent variables.
Normality of the distribution of the scores can be tested using
histograms, the values of skewness and kurtosis, or using tests such
as Shapiro-Wilk or Kolmogorov-Smirnov.
ASSUMPTION#6
• There needs to be homogeneity of variances for each
combination of the groups of the two independent variables.
• Test this assumption in SPSS Statistics using Levene’s test or the
Brown-Forsythe Test for homogeneity of variances.
You can check assumptions #4, #5 and #6 using SPSS Statistics.
Before doing this, you should make sure that your data meets
assumptions #1, #2 and #3, although you don’t need SPSS
Statistics to do this. Just remember that if you do not run the
statistical tests on these assumptions correctly, the results you get
when running a two-way ANOVA might not be valid.
GENERAL PROCEDURE
The null hypothesis for an ANOVA is that there is no significant
difference among the groups. The alternative hypothesis assumes that
there is at least one significant difference among the groups.
After cleaning the data, the researcher must test the assumptions of
ANOVA.
They must then calculate the F-ratio and the associated probability
value (p-value).
In general, if the p-value associated with the F is smaller than .05,
then the null hypothesis is rejected and the alternative hypothesis is
supported.
If the null hypothesis is rejected, one concludes that the means of all
the groups are not equal. Post-hoc tests tell the researcher which
groups are different from each other
EXPERIMENT
Let us take an example just for understanding
We want to know if there is any significant difference between the income
of females and males of rural, semi urban or urban residence.
Three Factors
One dependent- Income
Two independent- Gender and
Residence
Gender (Male, Female)
Now we will insert values
for all groups of both
independent variables as
following
Put Data
• Male, Female 9 each
• Rural, Semi Urban, Urban 6
each
Two effects
Now we will generate Main effect
Interaction
hypothesis. (separate
effect
But before that we know that effect)
we have three effects so we will
generate 3 null and 3
alternative hypothesis.
1. Effect of gender
on income 1. Effect of gender
2. Effect of or residence
residence on simultaneously
income income
HYPOTHESIS
Null hypothesis HO = μ1= μ2 = Alternate hypothesis Ha =
μ3 μ1≠μ2 ≠μ3
1. No significant difference 1. There is significant difference
between female and male between female and male
income. income.
2. No significant difference in 2. There is significant difference
income of rural, semi in income of rural, semi
urban and urban.
urban and urban.
3. There is significant effect of
3. No significant effect of gender and residence
gender and residence simultaneously on income
simultaneously on income.
Analyze > General linear
Model > Univariate
Add Dependent variable and Independent variable in the
following boxes and press OK. We will have the output.
For rejected
Ho:
Sig > 0.05 null hypothesis
accept
At least one
is different.
To find out Ho accepted 0.296>0.05
the different
one we Ho rejected 0.000>0.05
perform
POST HOC Ho accepted 0.976>0.05
test
To
perform
POST HOC
OK
This is showing that there is no
significant difference between the
income of rural and semi urban
residence but urban area income in
significantly different from other two
types of residence.
Significantly different Urban
Residence
EXAMPLE#2
For more SPSS options let's take another example
A researcher was interested in whether an individual's interest in
politics was influenced by their level of education and gender.
They recruited a random sample of participants to their study and
asked them about their interest in politics, which they scored from 0
to 100, with higher scores indicating a greater interest in politics.
The researcher then divided the participants by gender
(Male/Female) and then again by level of education
(School/College/University). Therefore, the dependent variable was
"interest in politics", and the two independent variables were
"gender" and "education".
The setup for this
example can be seen as;
Click Analyze > General Linear
Model > Univariate
Transfer the dependent and
independent variables
Click on plot, we will be having this univariate profile
plot
Now transfer education level to horizontal axis box
and gender to separate lines and click continue
Now transfer gender to horizontal axis box and
education level to separate lines and
click continue, You will be returned to
the Univariate dialogue box.
In univariate box, Click options, we will be having this univariate Options
box
Now transfer the interaction effect, "gender*education_level“ to display
box. Click the tests following tests you want to perform and click continue.
In univariate box, Click post hoc, we will be having this box.
Now transfer education level to post Hoc Tests for box. Click any test in
the followings you want to perform and click continue.
CONT…
When you click continue, you will return to the univariate box
Now press OK
You will have the outputs of the above tests, shown in the following
slides
You can interpret them as described in the above experiment.
Plot of the
results
THANK YOU
