TX_1~ABS:AT/ADD:TX_2~ABS:AT


1 http://journals.cihanuniversity.edu.iq/index.php/cuesj CUESJ 2022, 6 (2): 1-8

ReseaRch aRticle

Using Factor Analysis to Determine the Most Important Factors 
Affecting Student Absenteeism at Cihan University-Erbil
Hawkar Q. Birdawod

Department of Business Administration, Cihan University-Erbil, Kurdistan Region, Iraq

ABSTRACT

The review of the relevant literature reveals that the issue of absenteeism among students was not new. The researcher intended to explore 
the factors affecting absenteeism and to find a solution to solve this issue. For this purpose, a mixed methods research was designed. To 
analyze this problem, both quantitative and qualitative research methods were adopted in this study. In quantitative approach, a close-
ended questionnaire was developed to collect data. The sample comprised 470 students out of total population of 4892. A descriptive and 
inferential statistical techniques were used to analyze the data. The outcome of the study shows that common factors such as curriculum 
and organizational climate, transportation and recreation, administrative procedures, and psychological and economic issues all had an 
impact on students’ absences. Likewise, the results revealed that administrative and motivational factors, including personal organization 
and adaptations with performance to health and second housing, are the critical factors in the student’s absences. Furthermore, gender 
of the student plays a major role in the student’s absenteeism, and the results show that there is a significant difference between male and 
female students toward the absence of the students.

Keywords: Absenteeism factors, factor analysis, component method, principle component method, Cihan University-Erbil

INTRODUCTION

Factor analysis is an important tool of statistical methods associated with multi-dimensional variables, that is related to a set of phenomena or attributes that help a 
number of variables such as people. It is a statistical method, 
because it depends on the first argument at the expense of 
correlation coefficients between these phenomena. One tries 
to use the factor analysis to return the causes of a group of 
characteristics (we call it random variables) to a smaller 
number of factors which can be measured entirely and can 
be described in a simplified and accurate manner.[1] Factor 
analysis can also be defined as a multivariate analysis based 
on a set of hypotheses using the (correlation matrix) or 
(covariance matrix) to determine the (hypothetical factors) 
underlying the nature of interrelated relationships. Internal 
relationships are among a set of variables taken for a specific 
phenomenon. These factors are represented by new variables 
but with fewer original variables. The aim of the analysis is to 
describe and interpret the phenomena or characteristics of the 
variables on the basis of few factors as possible.[1,2]

One of the main important factors for the development 
of society and the country is the reform and improvement 
of the education system in universities. Many studies have 
been conducted for this purpose. As a result, a study has 
been conducted to assess and understand the factors that 
influence a student’s academic performance.[3] Another 

study focused on student feedback on the teaching methods 
used by university teachers.[4] A common topic that has been 
investigated to improve the education system in this region 
is the online education system, which has been discussed 
since the outbreak of the coronavirus and has become a 
supportive and alternative education in the universities 
of the Kurdistan Region.[5] Another interesting study is to 
determine the factors that cause university students to hate 
reading books.[6]

The study of absenteeism is very important for every 
institution and every teacher to improve the results. The 
reducing the rate of absenteeism is useful for making the 
students disciplined, punctual, and consistent.[7,8]

This study aims to find different factors of absenteeism at 
Cihan University-Erbil and find a solution to reduce it.

Corresponding Author: 
Hawkar Q. Birdawod, Department of Business Administration,  
Cihan University-Erbil, Kurdistan Region, Iraq.  
E-mail: hawkar.birdawod@cihanuniversity.edu.iq

Received: May 20, 2022 
Accepted: June 18, 2022 
Published: July 10, 2022

DOI: 10.24086/cuesj.v6n2y2022.pp1-8

Copyright © 2022 Hawkar Q. Birdawod. This is an open-access article distributed 
under the Creative Commons Attribution License (CC BY-NC-ND 4.0)

Cihan University-Erbil Scientific Journal (CUESJ)



Birdawod: Using factor analysis to determine student absenteeism

2 http://journals.cihanuniversity.edu.iq/index.php/cuesj CUESJ 2022, 6 (2): 1-8

The researcher’s effort was to sort out varied significant 
factors involved in the student’s absenteeism at the university 
level. It has always been a burning issue and especially 
nowadays since the government is concerned with improving 
and bringing positive changes to the educational sector.

Prominent level of absenteeism reported as missing 10% 
or more of the academic year has been a key indicator of 
student’s failure.[9,10]

Student absenteeism been given much attention today, 
but still it is uncontrollable issue. One thing is clear that this 
matter is not ignorable rather it needs greater attention and 
time to look into. Since new college students experience many 
challenges physically, socially, and mentally.[10,11]

Research Questions

Keeping in view the main objective of the study, the following 
research questions were made in light of the relevant literature. 
(1) What are the factors that cause absenteeism among 
university students? (2) Do the factors of absenteeism affect 
boys and girls students equally? (3) Are subject matter and 
the medium of instruction cause student’s absenteeism? (4) Is 
there any significant difference in the perspective of students 
in the factors of absenteeism?

Students with low attendance attribute their 
absenteeism to the poor relationship with teachers, university 
administration, and class fellows. The researcher made a 
standard about the low attendance by fixed a cut off line which 
will make decision making easy about the low attendance and 
the accurate attendance.

Objectives of the Study

The main objectives of the study are as follows:
1. To investigate the effects of absenteeism among students 

of Cihan University-Erbil
2. To present the basic literature review regarding 

absenteeism among students
3. To recommend a possible solution for absenteeism after 

the analysis of the data.

Research Hypothesis

Based on the objective and the conceptual framework of this 
study, null hypothesis is developed as follows:
H

01
: There is no significant difference between male and 

female students toward student’s absenteeism.
H

02
: There is no relationship between subject interest and 

student’s absenteeism.
H

03
: There is no relationship between lecturer’s skills and 

student’s absenteeism.
H

04
: There is no relationship between student’s attitude and 

student’s absenteeism.
H

05
: There is no relationship between health problems and 

student’s absenteeism.

The Objectives of Using the Factor 
Analysis

The main objectives of factor analysis can be summarized in 
the following points:

1. Interdependency and pattern delineation: The method of 
factor analysis explanation reveals the (patterns) separate 
of the relations between the variables and return the 
causes of those variables to the lowest number of factors, 
in which the strength of the relationship of each variable 
is determined by these patterns

2. Parsimony or data reduction: If we have a large number 
of private observations of a large set of variables, these 
data can be concentrated in the form of a few factors that 
represent the variables in describing the phenomenon and 
clarify relationship between them

3. Hypothesis testing: The factor analysis can be used to 
test the validity of the determinants of the type of factors 
affecting a set of variables, depending on the factor 
matrix

4. Data transformation: The global analysis helps to 
transform data into another image in which certain 
conditions can be applied to some statistical methods on it

5. Scaling: The method of factor analysis is useful in 
exploring new areas. Factor analysis reduces complex 
relationships between a set of variables to a simple linear 
image

6. Multicollineartiy: A factor analysis method contributes to 
addressing the problem of linear multiplicity, to convert 
variables associated with unrelated factors.[2,12-14]

LITERATURE REVIEW

Factor Model

The model of the factor analysis of p (p - dimensional) of the 
sample his size is n that it is based on a linear function of p the 
mean variables and m of the common factors, in which (M <p) 
and to (p) of the unique factors for each variable, the factor 
model will be as follows:[12,13]

 X F Upx px pxm mx px1 1 1 1� � �� �  (1)

Where:
X: Represents the random vector of observed variables.
µ: Represents the vector of variables.
A: The loading factors matrix represents the changes.
F: Is the random vector of the common factors selected from 
pvariables.
U: Represents the random vector of the only variables of the 
variables.

Basic Assumption of Factor Analysis

The basic hypothesis of factor analysis is based on the existence 
of correlations between a set of variables unstudied and that 
these correlations are the result of the existence of interrelated 
factors, in which the factor analysis seeks to explain these 
linkages with the least number of independent factors among 
them, this hypothesis assumes the standard value (standard 
Value) of the variables, which may be distributed in natural 
distribution with a mean of zero well as for the elimination of 
variables.[15,16]

Based on this hypothesis, the vector of the media and the 
variance of the variables will be zero vectors,

Var X I( ) =  and E X o( ) � ��



Birdawod: Using factor analysis to determine student absenteeism

3 http://journals.cihanuniversity.edu.iq/index.php/cuesj CUESJ 2022, 6 (2): 1-8

In this case, the factor model takes the following form:

  Z F Up p m m p* * * *1 1 1� ��  (2)

For the covariance matrix for each of the common factor 
drivers (F) and the only factors (U) assuming that, they are 
independent:

�
� �

� �

� �F
U

F U
FF FU

UF UU

m m m�

�
�

�

�
�

� �� � �
�� � �� �
�� � �� �

�

�

�
�
�

�

�




� � �nn

n m n m� �� �

�

�
�

�

�


Whereas:

Φ: Represents the heterogeneity matrix of the common factors 
F� � .

Ψ: The country matrix represents single factor variance.

As for the matrix of variance of the variables X� �  and (Σ) 
denoted by:

E X X p p( ') *��
So (Σ) that it is a symmetric positive definite and full rank 

matrix.

Moreover, since the goal in factor analysis is to estimate 
the parameters of the model, it was necessary to express the 
model (2) in a more appropriate form, since:

� � � � � �� E X X E AF U AF U( ) ( )( )
� � �� � � � �� �AE FF A AE FU E UF A E UU( ) ( ) ( ) ( )

The structural matrix (Ω), which represents the covariance 
between observed variables and factors, they are:

� � ��p m X F� �
� �( )

These hypotheses divide the total variation into three 
variations.

Common Variance

Represents a part of the total variance that is associated with 
the rest of the variables and is calculated from the coefficients 
of the general factors and symbolized by the symbol hj

2� � .[13,17]

  h a a aj j j jm
2

1
2

2
2 2� � � �...  (3)

Specific Variance

It represents a part of the total variance that is not associated 
with the other variables, but is associated with the same 
variable, which is part of the only factor variation that equals

   U b ej j j
2 2 2� �  (4)

Where:

Uj
2 : Is the only factor variation.

bj
2 : Variance of the variable j .

ej
2 : Error variance.

Error Variance

Which is not explained by the common factors that can be 
described as residual or error, is the variation resulting from 
errors in the sample drag or measurement or any changes that 
lead to data instability and symbolizes ej

2� � .[13,16]

  e h bj j j
2 2 21� � �( )  (5)

It is worth mentioning that factor analysis cannot be 
used if the sample size is less than 50 observations, and it is 
preferably when the sample size contains 100 observations or 
more.

The Commonalities

The standard value is the sum of the squares of the saturations 
of the factors of that variable, and it represents the common 
variance that is explained by the common factors extracted 
from the correlation matrix analysis, that is, it represents the 
extent of interference between the variables and the common 
factors: [13,17]

h a a aj j j jm
2

1
2

2
2 2� � � �...  Where j=1,2,3,………, p 

i=1,2,3,……, m

Or

h aj ij
i

m
2 2

1

�
�
�

Many of the factor analysis methods are needed when 
applying the factor analysis to an initial estimate of the 
quantities of communion hj

2� � and placing them in the diagonal 
elements of the correlation matrix (R) instead of the units. 
These methods are the method of analysis of the main factor 
used in our research, which needed to estimate these values 
and place them in the main diameter of the correlation 
matrix.[17-19]

Many of the factor analysis methods, including the main 
factor analysis method, need when used to a preliminary 
estimate of the quantities of commonness and put them in 
the diagonal elements of the correlation matrix instead of the 
units; then, it is called the reduced correlation matrix, and one 
of the characteristics of the common values is that they are 
always positive values, Its value lies between zero and one 
(because it is part of the total variance, which is equal to one), 
that is, it: [14,16,19]

0 12≤ ≤hj

Factor Analysis Methods

There are several ways to estimate the matrix of factor loading 
for the first solution, the following is the most common:

1. Principal components method
2. Factor method principal
3. Method maximum – likelihood
4. Image method
5. Unweighted least squares
6. Generalized least squares
7. Alpha method



Birdawod: Using factor analysis to determine student absenteeism

4 http://journals.cihanuniversity.edu.iq/index.php/cuesj CUESJ 2022, 6 (2): 1-8

8. The centered method
9. Rao method.

We will explain the main vehicle method, for 
adoption in the applied side, because it is more accurate in 
estimation.[15,20,21]

Principle Component Method

The basic idea of this method is to find the main universes, the 
number of which is equal to the number of studied variables 
(X

j
) where (j=1,2,3,……,p) that follow the multivariate 

normal distribution with the aver mean of the population ( )µ
and the covariance and covariance matrix (Σ), meaning that 
( , )� � � X  and then choose the first component of the main 
components, which is modified to find the following 
model:[16,19,22,23]

X L F L F L F U

X L F L F

m m

p p p

1 11 1 12 2 1 1

1 1 2 2

� � � � �

� � �

...............

.................� �

�

�
�

�
�L F Upm m p

 
(6)

where:
F

1…
F

m
: Represent the unrelated general factors that were 

extracted from (p) the variables.
L

ji
: Represents the factor loading (i) of the variable (j).

U
1
…U

p
: Are the only factors

METHODOLOGY

The results of this study will be based on the literature 
review and the responses collected from students through 
questionnaires. The response rate was appropriate to analyze 
the data. Data were analyzed in percentage response of 
respondents and using factor analysis.

The sample size is 470 students out of total population 
of 4892. The sample was calculated based on (5%) margin of 
error.

The respondent was divided into 240 female students a 
51.06% and 230 of the respondents were male 48.94%.

The study was conducted on the basis of a sample of 470 
students selected randomly. The data were collected by survey 
questionnaire as a mean tool. After classifying the data from 
the forms of the sample, each statement was calculated as a 
variable given symbols, using the statistical package (SPSS-
25). The data include a set of variables to explain the reasons 
for absence students.

RESULTS AND DISCUSSION

The purpose of this study is to determine the factors influencing 
students’ absences, to show the most important variables 
and their sequence in terms of their effect on the studied 
phenomenon for the method of factor analysis, the principal 
components were used to analyze the correlation matrix of the 
studied variables, and based on the matrix of the coefficients 
of the circulating factors in a manner (Varimax) and show the 
importance of each variable based on the relationship of this 
variable with other variables.

The number of moral factors was selected according to 
(Kaiser Scale) based on the characteristic values (the factor 
variation), keeping any factor with Eigen value greater than 
one. The significance of the loadings for each factor was 
determined on the basis of the comparison between factor 
loadings, where the largest load value was selected in each 
factor, and then, it is compared with other factor loads for 
same variables. The (Varimax) matrix was applied on all 
students and it was taken into consideration for the purpose 
of knowledge and distinguishing the reasons for absenteeism.

The Principal Components (P.C): The First 
Stage for All Students

In Table 1, we present the results obtained in this way for 470 
students and that represent the size of the sample (males and 
females).

It is noted from the table that the total number of factor 
variances is equal to 24, which represents the total variance 
of all the variables studied (the standard values). The shaded 
parts indicate the presence of the nine main significant factors 
effect on the reasons for absence of both genders together, 

Table 1: Analysis using the main compounds method for all 
students (male and female)

Factor Factor variance 
(distinguished 

value)

Variance 
ratio 
factor

Cumulative 
percentage 
of variance

1 4.295 17.897 17.897

2 2.321 9.67 27.568

3 1.887 7.861 35.428

4 1.556 6.481 41.91

5 1.379 5.745 47.655

6 1.266 5.276 52.931

7 1.197 4.987 57.918

8 1.139 4.748 62.666

9 1.064 4.433 67.099

10 0.865 3.605 70.704

11 0.85 3.543 74.247

12 0.821 3.419 77.666

13 0.703 2.931 80.597

14 0.652 2.716 83.313

15 0.571 2.38 85.693

16 0.55 2.294 87.986

17 0.496 2.067 90.053

18 0.455 1.896 91.949

19 0.41 1.707 93.656

20 0.382 1.59 95.246

21 0.344 1.434 96.681

22 0.328 1.365 98.046

23 0.267 1.113 99.158

24 0.202 0.842 100

Total 24 100



Birdawod: Using factor analysis to determine student absenteeism

5 http://journals.cihanuniversity.edu.iq/index.php/cuesj CUESJ 2022, 6 (2): 1-8

which represent the number of factors whose value exceeds 
one. These nine factors explain a percentage (67.099%) of 
the total variance of variables explained by these nine factors. 
Although they explain different percentages of variation, but 
they important in determining the variables affecting the 
absence of students and these nine factors are explained, 
respectively, 17.897%, 9.670%, 7.861%, 6.481%, 5.745%, 
5.276%, 4.987%, 4.748%, and 4.443% of the total variance.

First Factor

This factor is important in influencing the causes of absence, 
where it explains (17.897%) of the total variance. This factor 
is saturated with significant saturation for the following 
variables and according in sequence: depending on the book 
only to explaining the academic subjects X21 and by amount 
of 0.696 and the value of communality is 0.573, difficulty of a 
number of subjects x22 by amount of 0.674 and the value of 
communality is 0.625, incompatibility between students X17 
by amount of 0.614 and the value of communality is 0.539, 
the non-encouraging way of teachers in presenting the course 
material X2 by amount of 0.570 and the value of communality 
is 0.706, the weakness of the humanitarian relations between 
teachers and students X1 by amount of 0.551 and the value 
of communality is 0.714, student unwillingness to education 
X7 by amount of 0.511, and the value of communality 0.612. 
The weakness of academic subjects to motivate student X20 
by amount of 0.485 and the value of communality is 0.644 
within the saturation of this factor and in both genders and 
the quantities shown in the shaded parts of the table. This 
factor can be called (scientific) factor which is an important 
indicator to determine the reasons for absence of students in 
both genders.

This factor can be called the curriculum factor and the social 
and organizational climate. It can be said that the depending 
on the book in the commentary may be difficult to understand 
the student and that the lack of the introduction of examples 
and evidence may lead the student to a state of helplessness 
and lack of desire to lecture and then evade attending lectures 
on this side, and on the other hand, it can be said that the 
lack of an adequate social climate in the college reflects the 
negative effects on harmony which leads the student to search 
for other groups with them and, thus, was always absent. On 
the other hand, there is a lack of interest in the humanitarian 
aspect in dealing with students and weakness in consideration 
about their feelings, desire, and circumstances. In addition, the 
limited number of teachers makes it difficult to deal with both 
academic as well as the human side of the student. Therefore, 
understanding the students’ circumstances can be a helpful 
tool to decrease absenteeism.

In particular, the modern literature in the field of 
education and psychology refers to the importance of using 
psychological methods to link the subject to the needs of 
students and their interests and tendencies, all this leads to 
the departure of students from the study schedule and then 
their absence from lectures.

Second Factor

This factor is very important and comes in second place 
in terms of importance, which it interprets (9.670%) of 

the total variance and this factor satisfies a significant 
saturation of the following variables and in sequence, 
Unhealthy conditions in the accommodation X24 by 
amount of 0.845 and the value of communality is 0.775, 
failure to provide appropriate classroom environment X8 
by amount of 0.845% and the value of communality 0.755, 
and also poor living conditions of university students X6 by 
amount of 0.626 and the value of communality is 0.612. 
The weakness of the moral imprints of this factor in both 
genders are called the second administrative and scientific 
factor.

This factor can be called accommodation factor 
and economy first. The problem of student stability is a 
fundamental factor affecting the extent of his commitment to 
the continuation, especially in the beginning of the academic 
course. Lack of good health conditions in the accommodation 
of the heating and furniture and other conditions can be 
leading to infection diseases. Hence, it can be counted among 
the reasons for the absence of students from this permanence 
on the one hand, and on the other hand, a number of students 
from outside the center of the province maybe delay in 
obtaining accommodation due to the frequent procedures and 
complexities of routine as well as the concern of providing 
accommodation that burdens the students. This will result in 
the inability of students to connect to the school, and on the 
other hand, the nature of the economic conditions experienced 
by the student, which reflected the impact especially on the 
students’ ability to maintain their commitment due to the 
high wages of travel compared to the potential of students, 
especially those who suffer from poor living conditions, 
constant absences.

Third Factor

This factor comes in third place in terms of importance, it 
explains 7.861% of the total variance and saturated this factor 
by amount of 0.639, 0.795 and the value of communality is 
0.745, 0.676 of the variables lack of transportation facilities 
X5, and lack of comfort in university campuses X16. This factor 
can be called (transportation and recreational) factor. The lack 
of means of transport and the inability of the student to pay 
the transportation fees may result in a lack of commitment. 
On the other hand, the absence of students may sometimes 
refer to psychological reasons related to the student’s need 
for resting, so the lack of comfort causes the student to feel a 
sense of distress and tension and resort to other places away 
from the college, which leads the student to the absence of 
permanence.

Fourth Factor

This factor comes in fourth place in terms of importance, it 
explains 6.481% of the total variance and saturated this factor 
by amount of 0.691, 0.805 and the value of communality is 
0.599, 0.744 of the variables unclear vision of future career for 
college graduates X12 and Management delay announcement 
of results X10. This factor can be called (Future and 
administrative) factor. As we say, this factor can be referred to 
the acceptance controls, as well as the lack of the future, which 
affects in some way the motivation of the students negatively 
and their desire for continuous work, so he suffers from a 



Birdawod: Using factor analysis to determine student absenteeism

6 http://journals.cihanuniversity.edu.iq/index.php/cuesj CUESJ 2022, 6 (2): 1-8

Table 2 : (Loading matrix) Moral factors and common quantities of all the factors produced by the main compound method after rotation 
for all students (male and female)

Variable First 
factor

Second 
factor

Third 
factor

Forth 
factor

Fifth 
factor

Sixth 
factor

Seventh 
factor

Eighth 
factor

Ninth 
factor

Dispersion

X1 0.551 −0.09 0.113 −0.06 0.538 −0.15 −0.2 −0.171 0.08 0.714

X2 0.57 −0.252 −0.06 0.04 0.119 0.281 −0.14 −0.137 0.424 0.706

X3 0.102 0.204 0.122 0.193 0.005 0.045 0.759 0.051 −0.07 0.69

X4 0.081 0.413 0.057 0.067 0.583 0.168 0.145 0.232 −0.11 0.639

X5 0.045 0.131 0.759 −0.17 0.183 0.138 0.03 0.243 0.085 0.745

X6 −0.018 0.626 0.375 0.113 0.181 −0.06 0.135 −0.117 0.049 0.616

X7 0.511 0.42 0.359 0.254 0.415 0.139 −0.079 0.057 −0.14 0.612

X8 0.099 0.845 −0.02 −0.09 −0.03 0.108 −0.015 0.015 0.105 0.755

X9 −0.101 0.221 0.143 −0.02 0.023 0.015 −0.023 0.038 0.811 0.74

X10 0.074 −0.034 −0.12 0.691 0.153 −0.04 0.215 −0.049 −0.17 0.599

X11 0.422 0.225 0.265 0.188 −0.01 0.154 −0.433 0.145 −0.3 0.657

X12 0.07 0.001 0.164 0.805 −0 −0.16 −0.073 0.14 0.121 0.744

X13 0.113 0.269 0.328 0.027 −0.05 0.721 0.034 −0.149 −0.07 0.745

X14 0.387 −0.043 0.333 −0.35 0.346 −0 0.461 0.053 −0.03 0.724

X15 −0.103 0.055 0.085 0.072 0.713 0.055 0.039 0.017 0.064 0.543

X16 0.241 0.003 0.639 0.364 0.067 −0.05 0.201 −0.065 0.155 0.676

X17 0.614 0.179 0.117 0.152 0.042 0.026 0.257 −0.082 −0.01 0.539

X18 −0.036 −0.04 0.002 −0.24 0.056 0.713 −0.078 −0.105 0.033 0.589

X19 −0.049 −0.107 −0.32 0.052 0.288 0.556 0.219 0.263 0.108 0.641

X20 0.485 0.132 −0.05 0.196 −0.18 −0.06 0.183 0.439 0.299 0.644

X21 0.696 0.137 0.21 −0.1 −0.07 −0.07 −0.028 0.054 −0.06 0.573

X22 0.674 0.048 −0.16 0.169 0.002 0.049 0.088 0.234 −0.22 0.625

X23 −0.052 0.109 −0.13 −0.03 −0.11 0.119 0.016 −0.867 0.024 0.812

X24 0.099 0.859 −0 −0.03 0.083 −0.04 0.09 −0.053 0.081 0.775

%Variance 
Ratio 
Factor

17.9 9.67 7.861 6.481 5.745 5.276 4.987 4.748 4.433

psychological condition that is directly make him/her unstable 
in his time and presence.

Fifth Factor

This factor comes in fifth place in terms of importance, it 
explains (5.745%) of the total variance and saturated this 
factor by amount of 0.713, 0.583 and the value of communality 
is 0.639, 0.543 of the variables Various personal and family 
problems X15 and students work during or after university X4. 
This factor can be called (Social) factor. Many personal and 
family problems add to the sense of increasing the burden of 
work, which enables them to maintain their commitment to 
sustainability. On the other hand, the poor economic situation 
of the student reflected its effects, especially to the potential 
of the students and the extent of their commitment to full 
time, some of them to work despite being a student to improve 
economic level.

Sixth Factor

This factor comes in sixth place in terms of importance, it 
explains 5.745% of the total variance. This factor is saturated 
with a significant saturation of the following variables and 
in sequence: A number of students were preoccupied with 
relationships with others X13 by amount of 0.721 and the 
value of communality is 0.745. There are also two variables 
poor follow-up by the administration to students’ absences 
X18 and strong friendship bonds among students X19 by 
amount of 0.713, 0.756 and the value of communality is 
0.589, 0641. Respectively and sequentially, this factor may 
be referred to the (first administrative) or the motivational. 
The weak follow-up of the administration of the students’ 
absences affects the motivation of the students negatively and 
their desire for continue as well as the existence of a range 
of psychological and social needs are not saturated students, 



Birdawod: Using factor analysis to determine student absenteeism

7 http://journals.cihanuniversity.edu.iq/index.php/cuesj CUESJ 2022, 6 (2): 1-8

some of them are personal needs and their interests and need 
any affiliation to others, so their motivation is an important 
issue in terms of students to stay away from the study, because 
they do not agree and their needs and tendencies which leads 
to their departure from permanence.

Seventh Factor

This factor comes in seventh place in terms of importance, 
it explains %4.987 of the total variance and this factor is 
saturated with a significant saturation of the following variables 
and in sequence: Poor organization of the study schedule X3 
by amount of 0.759 and the value of communality is 0.690, 
Explanation of the subject by the teacher in a language far 
from the language of the student X14 and frequent daily 
examinations by a number of teachers X11 by amounts of 
0.461, 0.433 and the value of communality is 0.657, 0.724. The 
weakness of the moral imprints of this factor in both genders 
are called the second administrative and scientific factor. 
These three variables are called the second administrative and 
scientific factor.

Eighth Factor

This factor comes in seventh place in terms of importance, it 
explains 4.748% of the total variance and this factor is saturated 
with a significant saturation of the following variables and in 
sequence: The health situation of the students X23 by amount 
of 0.867 and the value of communality is 0.812. Only within 
the moral parameters of this factor can be called (health) 
factor. Since the absence of a number of students is always 
attributed to the suffering of health, as the infection of some 
diseases, especially cold diseases and the associated drugs, due 
to the siege leads to the student’s immaturity to physical and 
psychological rest and avoid it from work so can be counted 
among the reasons for the student’s absence.

Ninth Factor

This factor is ranked ninth and most important in terms of 
importance. It explains 4.433% of the total variance, and this 
factor satisfies a significant saturation of the variant of long 
distance from the university X9 by amount of 0.811, and the 
value of communality is 0.740. The ninth factor can be called 
(accommodation)

CONCLUSIONS

After addressing the applicable aspects of the study, and 
obtaining the results of the implementation of the principal of 
components method, the researcher came with the following 
conclusions:
1. During the work on the factor analysis for all students, the 

researcher found that there are nine main moral factors 
that allow us to determine the main effective reasons 
(variables) that lead to student’s absence for both genders 
and each of them individually

2. The study revealed that the explained ratio of total 
variance is the nine factors in cases (all students, only 
females, only males) equal (67.009%, 74.014%, and 
72.585%), respectively, this means that the explained 
ratio of total variance analysis that been done separately 

for each gender has increased comparing to the explained 
ratio in the analysis of both genders, and that assures 
our assumptions of importance of doing analysis of each 
gender individually, to get a better result

3. The study shows that the most important variables that 
have moral effects on students’ absence are curriculum 
and organizational climate, transportation and recreation, 
administrative procedures, and psychological and 
economic issues. Administrative and motivational factors 
including: personal organization and adaptations with 
performance to health and second housing. For females, 
living and economy, personal adaptation to the course 
and curriculum, admission and graduation regulations, 
psychological, health and administrative, transport and 
recreation, acceptance procedures, organizational and 
physiological climate, motivation, for males, curriculum 
climate and human relations, housing, economics, 
administrative management, admission controls and 
administrative procedures, motivation, recreation, 
personal adjustments, and permanence and health

4. Differential results of the factor analysis among both 
genders means that the order or sequence of the important 
variables that effect the female absence are different from 
the order or sequence of male’s absence variable. Thus, 
that assure our assumptions of doing the analysis of 
each gender individually, the purpose is to determine the 
reasons that lead to absence of gender individually

5. Not giving the real reasons of absence by students may 
prevent the desired results from being obtained.

RECOMMENDATIONS

The following recommendations can be made in light of the 
study conclusion:
1. The study assists the determination of main factors that 

affect students’ absence (and for each gender individually); 
hence, the study recommends the importance of doing 
researches and studies on the same topic, and take other 
variables (reasons) in consideration, and for greater number 
of students to come up with a valid recommendations and 
that’s for spotting the important reasons to reduce the 
phenomenon of absence at the university

2. The importance of taking the principles of humanitarian 
relationships into account for interrelationship between 
teachers with students

3. Use interesting and affective teaching methods, in 
a way that enriches class environment with fruitful 
communications among teachers, and students on the 
other hand. Furthermore, encouraging students to study 
and find other academic resources to overcome the 
difficulties related to certain subjects

4. Accommodate students for their necessities, especially 
providing transportation, provide suitable job 
opportunities for students, particularly those in need, 
weather inside the university or in coordination with 
organizations, as well as providing financial support to 
facilitate their affairs

5. The need to apply instructions and guidelines, especially 
in regard to students’ absence by assigning part of the 
passing grade according to attendance

6. Minimize the routine procedures regarding registration of 



Birdawod: Using factor analysis to determine student absenteeism

8 http://journals.cihanuniversity.edu.iq/index.php/cuesj CUESJ 2022, 6 (2): 1-8

students in the university and taking in consideration the 
importance of students desires to do that

7. Care for the cleanliness of student’s accommodation and 
the provision of health condition to avoid the possibility 
students to be infected by diseases.

REFERENCES
1. I. Ajzen. Attitudinal vs. normative messages: An investigation of 

the differential effects of persuasive communications on behavior. 
Sociometry, vol. 34, no. 2, pp. 263-280, 1971.

2. K. V. Mardia, J. T. Kent and J. M. Bibby. Multivariate Analysis. 
London, England: Academic Press, 1979.

3. N. H. Mahmood, S. H. Murad and K. K. Kakamad. Ordinal logistic 
regression for students academic performance in Kurdistan 
region of Iraq. Information Management and Business Review, 
vol. 10, no. 2, pp. 17-22, 2018.

4. D. H. Kadir and A. W. Omer. Implementing analysis of ordinal 
regression model on student’s feedback response. Cihan 
University-Erbil Journal of Humanities and Social Sciences, vol. 5, 
no. 1. pp. 45-49, 2021.

5. N. H. Mahmood, D. H. Kadir and H. Q. Birdawod. The full 
factorial design approach to determine the attitude of university 
lecturers towards e-learning and online teaching due to the 
covid-19 pandemic. Cihan University-Erbil Scientific Journal, 
vol. 6, no. 1. pp. 20-25, 2022.

6. H. Blbas and D. H. Kadir. An application of factor analysis to 
identify the most effective reasons that university students hate 
to read books. International Journal of Innovation, Creativity and 
Change, vol. 6, no. 2, pp. 251-265, 2019.

7. T. W. Anderson. An Introduction to Multivariate Statistical 
Analysis. 2nd ed. New York: ‎John Wiley and Sons, 1984.

8. W. R. Dillon and M. Goldstein. Multivariate Analysis methods and 
Application. New York: John Wiley and Sons, 1984.

9. R. Balfanz and V. Byrnes. The importance of being in school: 
A report on absenteeism in the nation’s public schools. The 
Education Digest, vol. 78, no. 2, p. 4, 2012.

10. P. Kousalya, V. Ravindranath and K. Vizayakumar. Student 
absenteeism in engineering colleges: Evaluation of alternatives 
using AHP. Advances in Decision Sciences, vol. 2006, p. 058232, 2006.

11. S. M. Abdelrahman and A. M. Abdelkader. The influencing factors 
of absenteeism among nursing students. Journal of Nursing 
Education and Practice, vol.7, no. 10, p. 64, 2017.

12. C. Chatfield and A. J. Collins. Introduction to Multivariate 

Analysis. London: Chapman and Hall, 1982.
13. T. H. Kayyali. A Study of the Application of Cluster Analysis Models 

with A Comparison with the Factor Analysis Method, A Master’s Thesis 
Submitted to the Statistics Department-College of Administration 
and Economics. Iraq: Al-Mustansiriya University, 1989.

14. M. A. Al-Nuaimi. Econometric Theory. Iraq: Al-Mustansiriya 
University, 1991.

15. K. M. Al-Rawi. Introduction to Regression Analysis. 1st ed. Iraq: 
Mosul University, Directorate of Dar Al-Kutub for Printing and 
Publishing, 1987.

16. L. E. Kirk. The Use of Multiple Analysis in Diagnosing Gallbladder 
Diseases and the Factors Affecting it, A Master’s Thesis Submitted 
to the Department of Statistics College of Administration and 
Economics. Erbil: Salah al-Din University, 2002.

17. H. Q. Yalda. Using Factor Analysis to Study the Factors Affecting 
Some Diseases of the Nervous System, a Master’s Thesis Submitted 
to the Department of Statistics College of Administration and 
Economics. Erbil: Salah al-Din University, 2000.

18. N. Nkansah, S. Ninson, B. F. Owusu and O. L. Prempeh. The 
Impact of Absenteeism on the Academic Performance of Pupils of 
Ebom-Bomfa JHS. Unpublished Dissertation. University of Cape 
Coast, 2017.

19. J. A. Al-Mahdawi. An Analytical Statistical Study on the Factors 
Affecting Juvenile Delinquency, a Master’s Thesis Submitted to the 
Department of Statistics, College of Administration and Economics. 
Iraq: University of Baghdad, 1987.

20. N. Wadesango and S. Machingambi. Causes and structural effects 
of student absenteeism: A case study of three South African 
Universities. Journal of Social Sciences, vol. 26, no. 2, pp. 89-97, 
2011.

21. A. Al-Sabawi. Organizational Knowledge and its impact on 
Determining the Entrances to the Formulation of Strategy: A Field 
Study of the Opinions of Senior Management in a Sample of Joint 
Stock Companies in the City of Mosul. Rafidain Development 
Journal, College of Administration and Economics University of 
Mosul, 1999.

22. G. Pehlivan. The school absenteeism among high school students: 
Contributing factors. Educational Sciences: Theory and Practice, 
vol. 16, no. 6, pp. 5-17, 2016.

23. H. Q. Pirdawd. Transformed and solving multi-objective linear 
programming problems to single-objective by using correlation 
technique. Cihan International Journal of Social Science, vol. 1, 
pp. 30-36, 2017.