ATTITUDE OF STUDENTS TOWARDS USAGE OF SOCIAL MEDIA IN MIZAN

TEPI UNIVERSITY TEPI CAMPUS STUDENTS

COLLAGE OF ENGINEERING AND TECHNOLOGY

DEPARTMENT OF HYDRAULIC AND WATER RESOURCES ENGINEERING

PREPARED BY: ELEMO ABRAHIM

ID N0: ETR 0372/11

AUGUST, 2021

TEPI, ETHIOPIA

i
Acknowledgement
First, I would like to extend our unshared thanks to GOD for providing me the opportunity to
join the university and to complete this research proposal.Then my advisor has provided us
the help and assistance. Therefore, we thank my advisor Gebre.M (Msc), who generously
devoted his time and knowledge to keep our on the right way through his guidance,
comments and suggestions. We would like to thank the department of statistics for providing
the internet access, which is help, full to get the required information and we would give
special thanks to our lab assistance Adis, for her experience and knowledge sharing in
various way. We also thank our family those helped me by finance and moral support. In
addition, we appreciated all respondents for their willingness to contribute the study by being
the source of necessary data and information

ii
ABSTRACT
This study was conduct on the attitude of students towards usage of social in Dilla
University in case of natural and computational science for under graduate students. social
media allow users to establish networks with other users. The total samples of 232 students
were selected in the main compus by using simple randam sampling technique. We used
primary data for this study, which was collect by distributing questionnaire for students of
seven departments in Dilla University collage of natural and computational science. The
method of data analysis used under this study was descriptive and inferential statistics.
Under descriptive 91.4% of male student are use face book while 8.6% of male student are do not
use face book. 94.4% of female student are use face book and 5.6% of female are do not use face
book. Under inferential part, chi-square test and binary logistic regression were used.Thep-
value less than alpha(0.05) that the variable of department, often you use face book, purpose,
internet access, speed of internet connection, average time spent to face book, spent to study
and face book or other social network effect our life are association with on the rate of usage
face book. While, p-value greater than alpha (0.05) the other independent variables do not
association on the rate of usage face book and other social network.Under logistic
regression, the odd of usage face book whose spent their time between three and five hour is
0.009 times less likely than that that spent their time below one hour. We recommended that
addiction to face book might lead to unnecessary bad consequence, so students and educators need to
see this problem before it get worse. Moreover, use face book kill study times so we recommended
that organization see the problem detailed make appropriate solution.

iii
 APPROVAL SHEET

The research proposal on “Attitude of students towards usage of social media in Dilla
University in main campus natural and computational science for under graduate
students” Submitted to department Statistics College of Natural and computational
Science, Dilla University

Submitted by:
___________________________ __________ ________________
__________________________ ____________ ________________
__________________________ ___________ ________________
Name of students signature date

Approved by:
________________________ _____________ ______________
Name of Advisor signature date
__________________________ ____________ _____________
Name of Dep’t Head signature date
1__________________________ __________________ _____________
Name of examiner signature date
2__________________________ __________________ ________________

iv
 Table of Contents
CHAPTER ONE........................................................................................................................1
1. INTRODUCTION..................................................................................................................1
1.1 Background of the Study..................................................................................................1
1.2 Statement of the Problem.................................................................................................2
1.3. Objectives of the Study...................................................................................................2
1.3.1 The General Objective...............................................................................................2
1.3.2 Specific Objectives....................................................................................................2
1.4. Significance of the Study.................................................................................................3
1.5 Scope of the study............................................................................................................3
CHAPTER TWO.......................................................................................................................4
2. LITERATURE REVIEW.......................................................................................................4
CHAPTER THREE....................................................................................................................8
1. METHODOLOGY OF THE STUDY...................................................................................8
3.1 Study Area........................................................................................................................8
3.1.1 Target Population.......................................................................................................8
3.1.2 Method of Data Collection........................................................................................8
3.1.3 Sampling Technique..................................................................................................8
3.1.4 Sample size determination.........................................................................................9
3.1.5 Variable of the Study.............................................................................................10
3.2 Method of Data Analysis................................................................................................10
3.2.1 Descriptive Statistics................................................................................................10
3.2.2 Inferential Statistics.................................................................................................11
3.2.3 Logistic Regression..................................................................................................11
3.2.4 Model Description...................................................................................................11
3.2.5. Goodness of Fit of the Model.................................................................................14
3.2.6. Likelihood-Ratio Test.............................................................................................14
3.2.7. The Hosmer and Lemeshow Test Statistic.............................................................14
3.2.8. The Wald statistics..................................................................................................15
3.2.9. Chi-square...............................................................................................................15
CHAPTER FOUR....................................................................................................................17
WORK PLAN AND BUDGET ALLOCATION....................................................................17
4.1. Time schedule................................................................................................................17
i
 4.2. Work Plan......................................................................................................................17
4.3 Budget plan.....................................................................................................................18
REFERANCE..........................................................................................................................19

ii
 CHAPTER ONE

1. INTRODUCTION

1.1 Background of the Study

Social media and social networks changed the way we communicate and interact with our
friends and peers. They also changed the way we consume media content. Social media gave
us an opportunity to become contributors and creators of digital content. Just a decade ago,
during the emerging phase, social media platforms were considered a novelty and their
commercial value was still questionable, at least outside the information technology (IT)
industry. However, a growing user base and saturation of traditional mass media resulted in
further commercial exploitation of social media platforms. According to eMarketers (2015),
social network spending reached $23.68 billion worldwide in 2015. Marketers are shifting
their budget from declining traditional media, such as print and TV, toward more dynamic
and interactive digital media, such as social media and mobile platforms (RSO Consulting,
2014).

The users range from primary school children to even senior citizens of 50 years and above.
(Young 2016)Throughout the years, other than to socialize, it has been proven useful in so
many ways, catering to health, social, and now even for educational purposes. There have
been studies done to test and see whether the social media, correlates to students’ grades and
performance in their academic achievement. Some of these studies were raven true, that there
was a connection between students’ grades and their usage of social media but researchers
are unsure whether it is a good correlation or not. And as of late, it was seen that now a day,
not only students use the social media, but their lecturers as well.

Some of them use for personal reasons; while others and most of them too, use social media
as a way to connect to their students online. Lecturers and students’ meetings are now held in
the virtual world, no longer practiced in the real world. This way is of course easier and faster
and much more interesting. It provides users with games to play, and socializing purposes are
believed to be the main reason why students have a social media account. Thus, having an
account could be useful for education purposes but it could cause a big distraction. Students
can get easily addicted to it, which leads to the act of procrastination and later, delay of
submission of assignments. This research on such issue may seem unimportant, but addiction

1
to social media may lead to unnecessary bad consequences, and students and educators need
to see this and address this problem before it gets worse.

1.2 Statement of the Problem

This study is mainly focused on the negative side effect of attitudes of students towards the
usage social networking technologies, which is social media addiction (young 1996).The
students who use social media regularly becomes addictive to social media (cromin
1996).How the examining use of Social media in Dilla University in main campus in case of
natural and computational science for undergraduate students context have focused on
students' use of the web application and its effects on the study time.

In order to fulfill the objectives of the research, the following questions are basic to conduct
the study:

1. How students addicted to social media?

2. What are the educational outcomes of the usage of social media in Dilla University in
main campus, in case of natural and computational science for undergraduate students?
3. Does the students’ use of social media have an effect on their academic performance?
4. What is the relationship between social media and academic performance of students in
Dilla University in main campus in case of natural and computational science for
undergraduate students?

1.3. Objectives of the Study

1.3.1 The General Objective

The general objective of the study is to assess the attitude of students towards the usage of
social media undergraduate students.

1.3.2 Specific Objectives

Based on the above statement of problem, the specific objectives of the study will be:

 To find out if the students are addicted to social media.

 To identify educational outcomes of the usage of social media in Dilla University in main
campus, in case of natural and computational science for undergraduate students.
 To investigate students perception on social media.

2
 To analyze the relationship between the social media and academic performance of
students in Dilla University in main campus, in case of natural and computational science
for undergraduate students.

1.4. Significance of the Study

This study aims to determine the attitude of students towards usage of social media and to
provide educational benefits to students. The study is benefits for all the society needs social
media and for Dilla University societies. And it will give a direction and evidence for policy
makers, planners and for those who have interest to study related to this study. And also use
to monitor the time spent on using social media, for knowing the degree of their addiction
towards the usage of social media, effects of social media on the student’s academic
performance.

1.5 Scope of the study

This study is conducted for attitude of students towards usage of social media in Dilla
University in main campus in case of natural and computational science for undergraduate
students. This study will be limited only for natural and computational science student for
undergraduate students.

3
 CHAPTER TWO

2. LITERATURE REVIEW

Theoretically, social media are interactive computer mediated technologies that facilitate the
creation or sharing of information, ideas, career interests and other forms of expression via
virtual communities and networks. we will define social media to establish a platform for
further understanding its role in facilitating learning process. Empirically Social media could
be defined as a group of Internet platforms build on the ideological and technological
foundations of Web 2.0 that allow the creation and exchange of user-generated content
(Kaplan and Haenlein, 2010). According to Bryer and Zavatarro (2011), social media gather
various technologies including blogs, wikis, networking platforms (social networks), virtual
worlds and media sharing tools that serve social purposes with the emphasis on social
interactions facilitation, collaboration possibilities and deliberation across stakeholders. As
the authors suggest, social media in the educational context has a wide variety of
implementation and use both in terms of outcomes and media through which it can be
facilitated. Additionally, different social media platforms contribute differently to the
learning experience. For example, wikis being tool for collaboration as opposed to blogs that
are more focused on authorship (Bryer and Zavatarro, 2011). However, each of the social
media platforms that can be used in an educational environment should focus on integrating
and contextualizing knowledge in the most efficient way

What some scholars emphasize is the contemporary susceptibility of social media with
constructivist learning theory and a learner-centered model. This approach focuses on
learning as a social process in which one constructs the knowledge, as opposed to simply
gaining it through the traditional model of learning (Duffy and Cunningham, 1996). George
Siemens (2005) in his article on a learning theory in the digital age has further explained the
existing learning theories in the context of social media, thus explaining that, as opposed to
traditional view, learning does not happen inside the person. Rather, numerous connections
are important to facilitate the process. Therefore, Siemens has proposed the new learning
theory view called connectivism that relies on the following principles (2005, p7):

4
• Learning and knowledge rests in diversity of opinions.
• Learning is a process of connecting specialized nodes or information sources.
•Learning may reside in non-human appliances.
• Capacity to know more is more critical than what is currently known.
• Nurturing and maintaining connections is needed to facilitate continual learning.
• Ability to see connections between fields, ideas and concepts is a core skill.
•Currency (accurate, up-to-date knowledge) is the intent of all connectivist learning .
• Decision-making is itself a learning process. Choosing what to learn and the meaning of
incoming information is seen through the lens of a shifting reality. While there is a right
answer now, it may be wrong tomorrow due to alterations in the information climate
affecting the decision.

Concisely, connectivism could be considered a networked social learning (Duke, Harper and
Johnston, 2013). In this context, the interactions and collaboration that social media can
provide in the learning process will contribute to knowledge construction through meaningful
and smart connections, contextualization and synthesis of learning problems. It can also
contribute to the more efficient assessment of learning outcomes. Moreover, social media
places students into familiar surroundings and helps advance information literacy and
metacognitive development (King, 2011). The fact that communication through social media
often times requires interpretation of presented or acquired data makes participation and
collaboration an important aspect of learning with.

Facebook exceeding 1.5 billion active users and many other platforms with hundreds of
millions of users (Statista, 2016a), social media should be considered a mainstream
communication platform in the developed world. Social media is an integral part of both our
professional and our private lives. Additionally, social media likely gained popularity as an
important communication and educational tool within higher education in response to the
high adoption rate among students and its potential role in improving student participation
(Draskovic, Caic and Kustrak, 2013). It could be argued that social media platforms present
educational, ethical, economic, and revolutionary changes in the organization and structure of
the higher education system worldwide (Meabon Bartow, 2014). Indeed, the support for
using social media platforms within the higher education environment is currently growing
(Ellefsen, 2016; Fasae and Adegbilero-Iwari, 2016; Taylor, McGrath-Champ and Clarkeburn,
2012; Kassens-Noor, 2012).

5
According to Foroughi (2011, p 3), the learning environment could benefit from the
application of social media for the lecturer-student interraction:

• Learning-related benefits: facilitation of collaborative learning, development of independent

learning skills, problem solving, team work, reflective learning, responsive feedback from
instructors, overcoming geographic isolation, peer-to peer support/feedback, visibility of
students work, integration of multimedia assets, and the creation of informal relations
between educators and students.
• Social benefits for students: increased engagement in course material, development of a
sense of community and transferable skills that enhance student employability, increased
sense of achievement, control, and ownership of their work.
• Benefits for institutions of higher education: increased cross-institutional collaborations,
support and community building outside the course environment, development of
communities of practice, increased student enrolment and retention.

Although social media introduced more active ways of learning for students, sometimes it
seems that instructors do not share same level of enthusiasm due to concern that less formal
communication via social media might erode their authority (Draskovic, Caic and Kustrak,
2013). Furthermore, utilization of social media as a teaching and communication tool requires
additional effort and proper level of computer literacy. Many of today’s students are highly
proficient in their use of digital media (Bodle, 2011). On the other hand, the overall level of
digital literacy and competency of faculty still requires some improvement and more
systematic approach to the teacher education (Tømte et al. 2015; Krumsvik, 2008).

To address the problems of student collaboration, engagement and interaction, many higher
education institutions use e-learning platforms known as Course Management Systems
(CMS) to ensure a more satisfactory and meaningful experience. Facilitating student
participation is not only a requirement in a contemporary classroom due to technological
changes, but it is strongly linked to learning outcomes. However, usage of CMS, although
appealing to lecturers due to its controlled collaborative features that such closed systems
enable, is not always efficient in terms of true collaboration and the sharing that social media
facilitates (Bryer and Chen, 2012). In addition, CMS as a learning tool cannot be entirely
considered in the context of social media and its benefits in learning/teaching environment
because it is essentially an online translation of traditional brick-and-mortar classroom

6
surroundings where students are treated as information receivers and not as information co-
creators (McLoughlin and Lee, 2008).

Social media is also important through virtual communication or what can be called a
computer-mediated communication (CMC). Regarding this particular channel, Mazer,
Murphy and Simonds (2007) argue that “the use of CMC in the instructional context could
ultimately have a positive effect on the student-teacher relationship, which can lead to
more positive student outcomes. Additionally, these findings may offer an explanation with
regard to communication between students and their teachers.“ In this particular article, the
authors discussed the teacher-disclosure through Facebook (i.e. the amount of information
that an instructor discloses to students) and the impact on student motivation, learning and
classroom climate. They found a positive correlation, meaning that higher disclosure
enhances mentioned factors. This is important because not only it provides a valuable insight
for instructors in terms of whether their students might view such activity as positive, but it
also provides instructors with a certain power of creating their digital image strategically,
which is usually harder to achieve in face-to-face communication. Lecturer’s presence on
Facebook can therefore not only enhance student motivation and learning, but also help them
brand themselves in a strategic way.

As many studies suggest (e.g. Ellefsen, 2016; Fasae and Adegbilero-Iwari, 2016; Sheldon,
2015; Draskovic, Caic and Kustrak, 2013; Pestek, Kadic-Maglajlic and Nozica, 2012;
Dabbagh and Kitsantas, 2011), social media has potential as an educational tool that could
improve student motivation and in-class participation levels. However, use and
implementation of social media in the classroom depends on both student and instructor.
Unfortunately, instructors typically share rather conservative attitudes towards using both
social media and contemporary technology, and prefer using more traditional media
(Mayberry et al., 2012; Roblyer et al., 2010). This gap between lecturers and students and
their perception’s of social media’s role in higher education (Draskovic, Caic and Kustrak,
2013) could be bridged with better understanding of student motivation and preferences
toward social media use for educational purposes.

7
 CHAPTER THREE

1. METHODOLOGY OF THE STUDY

3.1 Study Area

This study is conducted in Dilla university on analysis of the attitude of students towards the
usage of Social media in case of Natural and computational science for undergraduate
students. Dilla University is located in southern nation nationalities and peoples of Ethiopian
regional state, first established in 1996 in Gedeo zone and 359km far from capital city of
Ethiopia (Addis Abeba) and 86km from the regional capital city Hawassa. Dilla University
have four campuses, these are: Main campus, Odaya’a campus, Referral campus and
Hasedela campus and there is six colleges: Technology and Engineering, Business and
Economics, Health and Medical science, Social science and Humanities, Agriculture and
Natural Resource, and Natural and Computational science.

3.1.1 Target Population

The target population includes natural and computational science only undergraduate students
in Dilla University. Totally, there are 285 undergraduate students in natural and
computational science. From this 153 male students and 132 female students are there.

3.1.2 Method of Data Collection

In this study the data will be collected by using both primary and secondary data collected
method. Primary data collection in which I got original data from primary source by
questionnaire (A questionnaire is self- report instrument used for gathering information about
variables). And secondary data collection method in which I got data from the register in
order to determine the sample size.

3.1.3 Sampling Technique

Sampling Technique is a method selecting sample from entire population. For this study, we
will use simple random sampling. Simple random sampling is a method of selecting an item
from homogeneous population such that every possible sample of specific item has an equal

8
chance being selected (Cochran 3rd edition). The respondents were selected using simple
random sampling methods from total population number of Natural and computational
Science for undergraduate students in Dilla University. Since all undergraduate students of
natural and computational science students have homogeneous prospection towards social
media thus we can use simple random sampling.

3.1.4 Sample size determination

Sample size determination means selects sample from the target population or it is the act of
choosing the number of observations or replicates to include in a statistical sample. The
sample size is an important feature of any empirical study in which the goal is to make
inferences about a population from a sample and the need to have sufficient statistical power.

In order to have an optimum sample size, there are a number of issues /points one has to
take into account. Some of the issues are:

 Objective of the study

 Design of the research
 Cost constraint and plan for statistical analysis
 Degree of precision required for generalization
 Degree of confidence with which to conclude etc.

In view of the above information, we use the following formula to determine the sample size.
Therefore, for this study we uses the proportion of students those who have positive attitude
towards the usage of social media.

Question: What is an attitude of students towards usage of social media undergraduate

students? (Positive attitude = 8 and negative attitude = 2, sample size = 10), by simple pilot
survey we get p=0.8 and q = 1-p=1-0.8 = 0.2, d = 0.07

Level of significance which is 5%

If the fraction no/N (correction factor) is less than 5%, we use no=n, otherwise we use

no
n= n o Where
1+
N

Zα/2= is the accuracy level of significance taken as 1.96 for 5% confidence level

9
N = total population = 285 (total number of undergraduate students of natural and
computational sciences).(source Dilla University Registeral)

d= (7%) absolute margin of error that determined by researcher and used to define the
difference between parameters of variables and statistic.

z2 ❑ (1.96)2¿
no= 2
p∗q = 0.8∗0.2=¿94
d 2 (0.07)2

114/285 = 0.329>0.05, so we use the following formula

no 94
n= no = 94 = 70
1+ 1+
N 285

Where no= initial estimate sample size=94

n=estimated sample size= 70

3.1.5 Variable of the Study

Dependent variable:-the attitude of students toward usage of social media. (positive attitude
=1,negative attitude =0)

Independent variable:

 effect on study time

 Cumulative grade point average.

 Internet access.

 Time spent on social media.

 Usage of social media.

 Speed of internet connection.

 Purpose of social media.

 Income of students.

 Expense usage of social media.

10
 3.2 Method of Data Analysis
The study uses the following methods of data analysis on this research these:-

3.2.1 Descriptive Statistics

Descriptive Statistics is concerned with summary calculations, graphs, charts and tables. It
deals with describing data without attempting to infer anything that goes beyond the given set
of data. It consists of collection, organization, summarization and presentation of data in the
convenient and informative way

3.2.2 Inferential Statistics

Inferential Statistics is deals with making inferences and/or conclusions about a population
based on data obtained from a limited sample of observations. It consists of performing
hypothesis testing, determining relationships among variables and making predictions.

3.2.3 Logistic Regression

In this study the researcher use logistic regression model .The dependent variable is the
attitudes of students towards usage of social media and it is qualitative form which has two
possibilities; the student those who have positive or negative attitude. Logistic regression
analysis extends the techniques of regression analysis to research Situations in which the
outcome variable is categorical. Generally, the response variable is binary, such as (presence
or absence, success or failure etc) in logistic regression.

Assumption of Logistic Regression

Assumptions were should consider for the efficient use of logistic regression as given below
(Homer and Lemeshow, 1989).

 Logistic regression assumes meaningful coding of the variable. Logistic

coefficients were difficult to interpret if not coded meaningfully. The convention for binomial
logistic regression is to code the dependent class of interest as 1 and the other class as 0.
 Logistic regression does not assume a linear relationship between the
dependent and independent variables.
 The dependent variable must be categorical.
 The independent variable need not be interval, no normally distributed, no
linearly related and no equal variance within each group.
 The group must be mutually exclusive and exhaustive; a case can only be
one group and every case must be a member of one of the group.
11
 Larger samples are needed than for linear regression because maximum
likelihood coefficients are large sample estimates.
 The logit regression equation should have a linear relationship with the
logit form of the dependent variable.

3.2.4 Model Description

Binary logistic regression is most useful when you want to model the event probability for a
categorical response variable with two out come Since the probability of an event must lie
between 0 & 1, it is impractical to model probability with linear regression techniques,
because the linear regression model allows the dependent variable to take values greater than
1 or less than 0. The logistic regression model a type of generalized linear model that extends
the linear regression model by linking the range of real numbers to the 0-1 range.

By inverting the definition of the logistic function, we obtained as:

e +❑ x +❑ x … .+¿ x
1 1 2 2+ … i i

i = 1+ e+❑ x +❑ x +...… +¿ x ¿ ¿
1 1 2 2 i i

 Suppose that the attitude of students toward usage of social media is denoted by Y which
has binary values.

 When Y=1, it shows the attitude of students toward usage social media positive and

 Y=0, it shows the attitude of students toward social media negative.

If  is the probability that the attitude of students toward social media positive.

(1-) will be the probability that the attitude of student towards social media negative.

(x)
This means that will be the odds that, the selection attitude of students towards social
1−( x )
media.

In terms of odd ratio the logistic regression model can be written as

(x)
=exp (❑0 +❑1 x 1 +❑2 x 2 +…+❑¿ X k )
1−( x )

Which means that exp (i), i=1, 2…k is the factor by which the odds of occurrence of success
change by a unit increases in the i th independent variable.
12
Estimation of parameter
In classical logistic regression, the parameters could be estimated by maximum likelihood
estimation method. The maximum likelihood estimate of a parameter was the value that
maximizes the probability of the observed data. The parameter estimation in logistic
regression produce was outlined as follows: Let Y be the random binary response variable
whose value was either zero or one and X' = (x 1 , x2, x3, . . . ,xk) was a vector of k predicted
variables. The probability P(Y = 1/ x1, x2, x3, . . . ,xk ) was given by:

P ( Y =1/ x 1 , x 2 ,… , x k )=exp ⁡¿ ¿

The parameters of the above equation were estimated by maximum likelihood estimation
technique.

To apply the technique, each observation could be considered as Bernoulli trial and by
assumption that each yi was independent the jointed distribution of the observed values could
be written as P(Y1 = y1, Y2 = y2, . . . , Yn = yn) = P(Y1 = y1)P(Y2 = y2) … P(Yn = yn)

The probability of the ith observation given (x1i, x2i, x3i, . . . ,xki) was given by

P(Y = 1/ x1i, x2i, x3i, . . . ,xki ) = Pi(1-pi)1-yi

Where, i = 1, 2, 3, . . . ,n and n is the number of cases in the data. The likelihood function
for (β0 ,β1, β2,. . ., βk) given (y1, y2, y3, . . . , yn) can be expressed as

n
L ( β 0 , β 1 , β 2 … , β k / y 1 , y 2 , … , y k )=∏ Pi (1−Pi )1− y i

i =1

By substituting pi = p(Y = 1/ x1i, x2i, x3i, . . . ,xki) given above, we obtained

L (β0 β1 β2, . . ., βk/ y1, y2, y3, . . . , yn)

k
yi
n exp ⁡( β 0 + ∑ β j x j ) 1− y i
j=1 1
L ( β 0 , β 1 , β 2 … , β k / y 1 , y 2 , … , y k )=∏ {〔 k
〕 〔 k
〕
i =1
1+exp ⁡( β 0+ ∑ β j x j) exp ⁡( β0 + ∑ β j x j )
j=1 j=1

The log of likelihood function was given by

13
 k
yi

L=log ∏ {〔
i=1
n

{ exp ⁡( β 0 + ∑ β j x ji )
j=1
k
1+exp ⁡( β 0+ ∑ β j x ji )
j=1
〕 〔
1
k
exp ⁡(β 0 +∑ β j x ji )
j=1
〕
1− y i

}
This was equivalent to

n
L=∑ y i log 〔
(
exp β 0 + ∑ β j x ji
j=1
) n
〕+ ∑ ( 1− yi ) (
1
)
k k
i =1

(
1+exp β 0+ ∑ β j x ji
j=1
) i=1
exp ⁡( β 0 + ∑ β j x ji )
j=1

The estimates of parameters could be found by maximizing the equation using iterative
techniques such as Newton-Raphson method.

3.2.5. Goodness of Fit of the Model

Assessing goodness of fit involves investigating how close value predicted by the model with
that of observed values (Be Wick and Jonahtan, 2005) i.e. to investigate whether the given
data is good fitted or not. The comparison of observed predicted values using likelihood
function is based on the statistics called deviance.

8
D= -2∑ ¿¿ + (1- y t ¿ ln ¿)]
i=1

For purpose of assessing the significance of an independent variable, the value of D is

compared with and without the independent variables in the equation as given below:

x 2=D (model without the variable) - D (model with the variable).

The goodness of fit x 2 process evaluate predictors that are eliminated from the full model, or
predictors (and their interactions) that are added a smaller model.

3.2.6. Likelihood-Ratio Test

The likelihood ratio test statistic (G 2) is the test statistic comely used for assessing the overall
fit of logistic regression model. The likelihood ratio test uses the ratio of maximized value of
likelihood function for the full model (L1) over the maximized value of the likelihood
function for the simpler model (L0). The likelihood-ratio test statistic is given:

14
 Lo
2
G =−2 log ( )
L1
=−2 [ log ( Lo ) −log ( L1 ) ]=−2 [Lo −L1 ]

It is compared with distribution with 1 degree of freedom. This log transformation of the
likelihood functions yields a chi-squared statistic.

3.2.7. The Hosmer and Lemeshow Test Statistic

The final measure of model fit is the Hosmer and Lemeshow goodness-of-fit statistics, which
measures the correspondence between the actual and predicted values of the dependent
variable.

HO: the model is good fitted

H1: the model is not good fitted

The test statistics is

2
n
( O j−E j )
( )
2
G =∑
HL
j=0 E j ~ 2
E j (1− )
nj

where,

nj= Number of observations in the jth group

oj = Observed number of cases in the jth group

Ej = Expected number of cases in the jth group

Decision; if G2HL >= 2 with 1df reject the null hypotheses, or if the p-value <=0.05 we can
reject the null hypothesis and we conclude that the model is not good model.

3.2.8. The Wald statistics

The Wald statistics is an alternative test, which is commonly used to test the significance of
individual logistic regression coefficients for each independent variable (that is to test the null
hypothesis in logistic regression model that a particular logit coefficient is zero).If the Wald
test is not significant, then these explanatory variables can be omitted from the model. Wald
2statistics was used to test the significance of individual coefficients in the model and is
calculated as:

15
Z2 =¿2

Each Wald statistics is compared with 2 distribution with 1 degree of freedom. Wald
statistics is easy to calculate but their reliability is questionable, particularly for small
samples.

3.2.9. Chi-square
Chi-square test will be used to assess whether two categorical variable are associated.

Here chi-square test use for the test of independency,

Hypothesis test is the following

1. HO: The two variables (factor) of the element are not associated

H1: The two variables (factor) of the element are associated

2. Level of significance  =0.05

3. Test statistics

2 =¿ ¿ ¿ ¿

Where Oij=observed frequency

Eij= Expected frequency

4. The critical value is 2tab=2 (R-1) (C-1)

Where R=number of rows

C=number of columns

5. Decision rule Reject Ho if 2cal >2tab

Otherwise do not reject, where (R-1)(C-1)=degree freedom

But their reliability is questionable, particularly for small samples

16
 CHAPTER FOUR

WORK PLAN AND BUDGET ALLOCATION

A work plan is a schedule, chart or graphs that summary the different components of a survey
project and how they will be implemented in a logical and well organized way within specific
time period.

4.1. Time schedule

The time break down is the most important criteria for working effective and reliable
research. The time break down given for the study from November to Jun 2012E.C
In conducting survey a planning of time table should being drawn up in order to facilitate
planning and budgeting .Time schedule for field operation must take into account two key
aspects: list of survey activities and approximate time needed to perform each activity
In presenting time schedule, a bar chart approach was developed by HenryI. Gantt. A
schedule that summarizes the different component of a research proposal and how they will
be implementing.

4.2 Work Plan

Table 2: Duration of the study will be completed in 9 months

No Activities Nov Dec Jan Feb Mar Apr May June
.

1 Topic selection 

Development of 
research proposal
2

3 Proposal submission 

4 Data Preparation  

5 Data organization, 
analysis and
interpretation

6 Report writing 

7 Advisor contact       

8 Draft final research 

17
 9 Research submission 

10 Presentation 

4.3 Budget plan

Table 4.2 Budget Preparation.

Unit price Total Price

No Item Quantity
Birr Cent Birr Cent
1 Pen  1  9 00  9  00

2 Ruler  0  0  00  0  00

3 Calculator 1 150 00 150 00

4 Notebook  1  25  00  25  .5

5 Copying 71 0.65 00 46 00
questionnaire
6 Flash (8GB)  1  230  00  230  00
7 Mobile card 2 10 00 20
Total 480

REFERANCE

Bodle, (2011) Social Learning with Social Media: Expanding and Extending the
Communication Studies Classroom.
Bryer, T. A. and Zavattaro, S. (2011) Social media and public administration:
Cronin M.J (1996) global advantage on the internet from corporate connectivity to
international competitiveness. New York.
Dabbagh, N. and Kitsantas, A. (2011) Personal Learning Environments, social media and
self-regulated learning:
Draskovic, N., Caic, M. and Kustrak, A. (2013) Croatian perspective(s) on the lecturer
18
 student interaction through social media.
Duffy, T. M. and Cunningham, D. J. (1996) Constructivism
Duke, B., Harper, G. and Johnston, M. (2013) Connectivism as a Digital Age Learning
Theory.
Ellefsen, L. (2016) An Investigation into Perceptions of Facebook-use in Higher Education.
eMarketer (2015) Social Network Ad Spending to Hit $23.68 Billion Worldwide in 2015
[Online]: 20 February 2016].
Fasae, J.K. and Adegbilero-Iwari, I. (2016) Use of social media by science students in public
Universities in Southwest Nigeria.
Foroughi, A. (2011) A Research Framework for Evaluating the Effectiveness of
Implementation of Social Media in Higher Education
Hosmer d. and lemeshow s. (1989).applied logistic regression John Wiley and sons
Inc.New York.
Kaplan, A. M. and Haenlein, M. (2010) Users of the world, unite! The challenges and
Opportunities of social media
King, R. (2011) Metacognition: Information Literacy and Web 2.0 as an Instructional Tool.
Mazer, J.P., Murphy R.E. and Simonds C.J. (2007): The Effects of Computer-Mediate
Teacher Self-Disclosure on Student Motivation.
McLoughlin, C. and Lee, M. J. W. (2008) Future Learning Landscapes:
Meabon Bartow, S. (2014) Teaching with Social Media: Disrupting Present Day Public
Education.

Pestek, A., Kadic-Maglajlic, S. and Nozica, M. (2012) Implications of Web 2.0 Usage in
Higher Education.

Roblyer, M., McDaniel, M., Webb, M., Herman, J., & Witty, J. V. (2010) Findings on

social media in higher education:

RSO Consulting (2014) Global Ad Spend in 2015 [Online]. Available from:

http:// www.rso-consulting: 20 February 2016].
Sheldon, P. (2015) Understanding students’ reasons and gender differences in adding faculty
as social mesdia friends.

19
Siemens, G. (2005) Connectivism: A Learning Theory for the Digital Age.

Statista (2016a) Leading social networks worldwide as of January 2016 [Online].

12 February 2016].

Taylor, L., McGrath-Champ, S. And Clarkeburn, H. (2012) Supporting student self-study:

Tømte, C., Enochsson, A-B., Buskqvist, U. and Kårstein, A. (2015) Educating online

student teachers to master professional digital competence

Young K.S (1996) Internet addiction.

20