Assignment Title: Analysis of Variance

Course: Introduction to SPSS

Submitted By:

Haleema Batool (NUML-F19-22007)

M.Phil. 2nd : Education Department

Submitted To:

Dr Qurrat ul Ain Hina

Assistant Professor,

Department of Education

National University of Modern Languages

Analysis of Variance (ANOVA)

Introduction:

ANOVA is a statistical test used in SPSS. SPSS stands for Statistical Package for Social
Sciences. Three university students namely Norman, Haldlai and Dale introduced the statistical
package for social science in in Chicago Stanford university. It was initially released in 1968. It
is officially also named as IBM SPSS because it was acquired by IBM in 2009. But most
commonly it is referred to as SPSS. SPSS helps in data collection in research process and it also
gives output and result of the collected data once enter in the software. The other purpose of
SPSS is to operate the statistical test (Coverley, 2018). SPSS generate the following statistical
test :

1. t. Test
2. Binomial test
3. One-way ANOVA
4. Regression
5. Correlation
6. Paired test
7. Factor Analysis

ANOVA: Analysis of Variance :

In 1920 Ronald Fisher, a British statistician and biologist introduced ANOVA for the
first time. He defined the term analysis of variance (ANOVA) the difference or variance of mean
of one group to another group. As he was much curious to study about genetics , he used the
term Fisher’s F distribution as a part of statistical significance. He has developed many research
papers on statistics among them “theoretical statistics on mathematical foundation” published in
1922 and “application of student’s distribution” published in 1925 are the most famous papers of
Ronald Fisher.

Types of ANOVA :

1. One Way ANOVA:

If there is only one independent variable in ANOVA it is known as one-way ANOVA.

For example, innovative strategies.
 a. One-way between-groups ANOVA:

For this type of one-way ANOVA two variables are required. Within that three or more
than three categories are required for example if the variable is gender then its three
categories might be male, female and trans or for the variable of age three level can be
20-25 years, 26-30 years and 31-35 years. This one-way ANOVA identifies whether
there is difference among the mean scored of the dependent variable across its three level/
categories. In order to check whether these differences exist or not, post hoc test can be
used (Pallant,2005).

b. One-way repeated measures ANOVA:

It is needed in order to check the differences of one group of subjects measured of different
occasions and condition on the same scale. Wither it can also be taken by measuring the person
on three different questions using the same response. It also involves two variables i.e. the
independent variable and the dependent variables. It will tell us about the differences of three set
of scores on same scale in different occasion and conditions (Plallant,2005).

Procedure and steps of One way between group ANOVA with post hoc:

i. At the top of screen from the menu click on the option of Analyze, the next coming
option compare mean and one-way ANOVA.
ii. Next the two appeared boxes are to be filled with the dependent and independent
variables , click on the dependent variable i.e. the creative abilities and the independent
variable i.e. the gender or grade level.
iii. In the option button click on the option descriptive , homogeneity of variance test and
mean plot.
iv. Click on the option post hoc.
v. Click on continue and then ok.
2. Two Way ANOVA:

When there are two independent variables and one dependent variable is called two-way
ANOVA. For this we need three variables two categorical independent variables (e.g.
gender: male, female and trans and age group ; middle, young and old) and one continuous
 dependent variable e.g. job satisfaction. It identifies the effect of each categorical variable on
the dependent variable and identifies either there is a relationship between them or not. For
example, is there any difference between the job satisfaction level of male , female of trans or
either there is a difference among the job satisfaction level of middle, young and old people
i.e. is there a difference in the effect of age on job satisfaction or not. .

Procedure and steps for two-way ANOVA:

i. As same in the one-way ANOVA , click on the analyze from the top of the data view ,
click on general linear model and then click on univariate.
ii. click the dependent variable i.e. job satisfaction and move it to label of independent
variable .
iii. there is a label of fixed factors, click the independent variables i.e. the gender and age
group and move them to the label of fixed factors.
iv. From the option button, click on the option descriptive statistics, estimate of effect size
and they click on homogeneity test and then continue.
v. Click on the post hoc. On the left-hand side ,from the factor choose the independent
variable(s) that you want to check . to move it into post hoc test for section click on arrow
button . choose the test of your own interest and then click continue.
vi. Click the plot button . put the independent variable that has the group in the horizontal
box. In the box labelled separate lines , put the other independent variables . click on
Add. See the variable listed gender and age in the section labelled plots
vii. Lastly continue and then okay.

The generated tables will show the results of two-way ANOVA.

Three dimensions of ANOVA:

One Way ANOVA between group:

In order to check the differences between two group either they have a
significant difference in their means or not, ANOVA is used.

Two Way ANOVA without replication:

 It is when a researcher takes double test from a single group . for example, pretest and
posttest of students before and after teaching them using multimedia.

Two Way ANOVA with replication:

Testing the difference of two different groups whose members are working more
than one thing . for example , two groups of patients from different hospitals trying two different
therapies (Miller, 2018).

Advantages and disadvantages of ANOVA:

According to Landau and Everitt , 2004 following are the advantages and the disadvantages of
ANOVA;

Advantages:

a. It has a robust design.

b. The statistical power of data and results can be increased.
c. The interaction among factors can be identified.
d. Random variability can be reduced.
e. It checks the effect of one variable by controlling the first variable.
f. The overall error i.e. the false positive findings can be controlled.

Disadvantages:

a. We know that at least one group differ from others, when the hypothesis is rejected, but
with one-way ANOVA and multiple groups it may be difficult to determine which group
is different.
b. Assumptions are needed to be fulfilled.
1) ).

Application of One-Way ANOVA:

Following are the steps to apply one-way ANOVA on the data:

 1. Click on analyze at the top of screen and then go to the option compare mean and then
click on the option one-way ANOVA.
2. A dialogue box will be appeared having two boxes i.e. dependent list and the factor box.
3. Transfer the dependent variable i.e. the gender or age into the dependent list and the
independent variable in factor box using the arrow .
4. Click on post hock and within that and then click on continue (it is needed when there is
significant differences in the results).
5. Click on descriptive from the option button and then click on continue.
6. Click on the OK button

These two tables will be generated one named as descriptive and the second as ANOVA.
From these two tables certain values that are important for the final interpretation of ANOVA,
will be taken and an APA table will be generated using these values for interpreting the results.

Descriptive

Job satisfaction

N Mean Std. Deviation Std. Error 95% Confidence Interval for Mean Minimum Maximum

Lower Bound Upper Bound

Social Sciences 36 2.28 .659 .110 2.05 2.50 1 3

13 1.92 .494 .137 1.62 2.22 1 3
Management Sciences

Engineering 29 2.00 .845 .157 1.68 2.32 1 4

Computer Science 15 2.00 .655 .169 1.64 2.36 1 3

Total 93 2.10 .708 .073 1.95 2.24 1 4

ANOVA
Job satisfaction

Sum of Squares Df Mean Square F Sig.

Between Groups 1.984 3 .661 1.333 .269

Within Groups 44.145 89 .496
Total 46.129 92

Interpretation of ANOVA:
Table 1: Department vice Comparison of job satisfaction (ANOVA)
Table 1 shows the department vice comparison of employee job satisfaction. Here N is the
number of respondent and m is the difference in mean value that are not statistically significant.
social science has the highest and management science has the lowest mean among the four
different groups. The null hypothesis was there is no significant difference among the employee
job satisfaction department. This hypothesis can be accepted as the values of sig is .269 that is
greater than 0.05. if the values of significance id greater than 0.05 we can conclude that there is
no significant difference among the job satisfaction of employee in different departments. The F
value shows there is no variance between two groups.

Application of Two-Way ANOVA:

Sajid , 2016 in his article two-way ANOVA by hand , has given an example to find out the result
of Two-Way ANOVA by using statistical formula as, “We will do two-way ANOVA for
example, let’s start the calculation

Example: Suppose you want to determine whether the brand of laundry detergent used, and the
temperature affects the amount of dirt removed from your laundry. To this end, you buy two
detergents with the different brand (“Super” and “Best”) and choose three different temperature
levels (“cold”, “warm” and “hot”).

Then you divide your laundry randomly into “6*r” pile of equal size and assign each ‘r’ piles
into the combination of (“super” and “Best”) and (“cold”, “warm” and “hot”). In this example,
we are interested in testing the Null Hypothesis.

H(οD) = The amount of dirt removed does not depend on the type of detergent.

H(οT) = The amount of dirt removed does not depend on the temperature.

The example has two factors(factor detergent, factor temperature) at a=2(Super and Best) and
b=3(cold, warm and hot) levels. Thus, there are a*b = 3*2=6 different combination of detergent
and temperature with each combination. There is r=4 loads. (r is called the number of replicates).
This sums up to “n=a*b*r”=24=2*3*4 loads in total.
The amounts of Y(ijk) of dirt removed when washing sub pile k(k=1,2,3,4) with detergent
i(i=1,2) at temperature(j=1,2,3) are recorded in table below:-

We have calculated all the means like detergent mean(Md), temperature means (Mt) and mean of
every group combination.

Now what we only have to do is calculate the sum of squares(ss) and degree of freedom(df) for
temperature, detergent and interaction between factor and levels.

First calculate the SS(within)/df(within) we have already known how to calculate

SS(within)/df(within) in one-way ANOVA we calculated this but in two way ANOVA the
formula is different

STEP 1: Formula for calculation of SS(within) is:

Yijk is the elements in the groups.

Y‾(ij) is mean of combinations

When we put the values and do calculations with this formula, we will get SS(within) is

= (4 − 5)² + (5 − 5)² + (6 − 5)² + (5 − 5)²

+(7 − 9)² + (9 − 9)² + (8 − 9)² + (12 − 9)²

······

+(12 − 12)² + (13 − 12)² + (10 − 12)² + (13 − 12

= 38

Calculate the df(within):

df(within) = (r-1)*a*b = 3*2*3 = 18

Calculate MS(within):

MS(within) = SS(within)/df(within) = 38/18 = 2.1111

STEP 2: Calculate SS(detergent) and df(detergent) and MS(detergent)

Y¯(i) is the mean of detergent

Y¯ is the total mean detergent and temperature

= 4*3[(8-9)²+(10-9)²]

= 24

Calculate df(detergent):

df(detergent) = a-1= 2-1 = 1

Calculate MS(detergent):

MS(detergent) = SS(detergent)/df(detergent)

= 24/1= 24

STEP 3: Calculate the SS(temperature), df(temperature) and MS(temperature)

Y¯(i) is the mean of detergent

Y¯ is the total mean detergent and temperature

= 4*2*[(5 − 9)² + (11 − 9)² + (11 − 9)²]

= 192

Calculate df(temperature):

df(temperature) = b-1 = 3-1 = 2

Calculate MS(temperature):

MS(temperature) = SS(temperature)/df(temperature)

= 192/2 = 81

STEP 4: Calculate SS(interaction), df(interaction) and MS(interaction)

Y‾(ij) is mean of combinations

Y¯(i) is the mean of detergent

Y¯(j) is the mean of temperature

Y¯ is the total mean detergent and temperature

Calculate SS(interaction):

= 4 ×(5 − 8 − 5 + 9)² + (9 − 8 − 11 + 9)² + (110 − 8 − 11 + 9)² + · · · + (12 − 11 − 10 + 9)²

= 12

Calculate df(interaction):

df(interaction) = (a-1)*(b-1) = (2-1)*(3-1) = 2

Calculate MS(interaction):

MS(interaction) = SS(interaction)/df(interaction)

= 12/2

=6

Its time to calculate the F-test: Calculate critical F-value

MS(detergent)/MS(within) ~ F(df(detergent), df(within))

MS(temperature)/MS(within) ~ F(df(temperature), df(within))

MS(interaction)/MS(within) ~ F(df(interaction), df(within))

If you found the F-value less than the critical F-value then you will not be able to reject the null
hypothesis I explained and how to and from where to calculate the critical F-value.”

Summary:
Ronal Fisher introduced ANOVA in early 19s. The term became well known in 1925 after
appearing in Fisher’s book. It stands for analysis of variance that is used to compare the mean
value of different group and to identify the differences among the means of different group. The
value of ANOVA is denoted by F. There are two types of ANOVA one-way ANOVA and two-
way ANOVA. One-way ANOVA is needed in order to check the differences of one group of
subjects measured of different occasions and condition on the same scale. On the other hand,
two-way ANOVA is needed when there are two independent variables and one dependent
variable is called two-way ANOVA. For this we need three variables two categorical
independent variables (e.g. gender: male, female and trans and age group ; middle, young and
old) and one continuous dependent variable e.g. job satisfaction.