MEKDELA AMBA UNIVERSITY

COLLEGE OF NATURAL AND COMPUTATIONAL

DEPARTMENT OF STATISTICS

FACTORS AFFECTING THE USE OF FAMILY PLANNING: IN

THE CASE OF GIMBA TOWN ADMINISTRATION
BY:
MOGES TILAHUN
ADDISU BEZA
YORDANOS YISMAW

ADVISOR:
FREZER TILAHUN (MSc.)

A PROPOSAL SUBMITTED TO THE DEPARTMENT OF STATISTICS, IN

PARTIAL FULFILLMENT OF THE REQUIREMENT FOR THE DEGREE OF
BACHELOR OF SCIENCE IN STATISTICS

June, 2024

Tulu Awulia, Ethiopia

I
 Table of Content
Executive Summary........................................................................................................................................V
1. INTRODUCTION....................................................................................................................................1
1.1. Background of the Study.......................................................................................1
1.2. Statement of the Problem......................................................................................2
1.3. OBJECTIVES.......................................................................................................3
1.3.1. General Objective..........................................................................................3
1.3.2. Specific Objectives........................................................................................3
1.4. Scope of the Study................................................................................................4
1.5. Significance of the Study......................................................................................4
2. Literature Review......................................................................................................................................5
2.1. Theoretical literature.............................................................................................5
2.2. Empirical literature...............................................................................................6
2.2.1. Education of the women................................................................................7
2.2.2. Financial Impact on Family Planning............................................................7
2.2.3. Physical And Mental Well-Being..................................................................7
2.2.4. Age of the women..........................................................................................8
2.2.5. Occupation of the women..............................................................................8
2.2.6. Religion..........................................................................................................8
2.2.7. Number of children large...............................................................................8
3. METHODOLOGY AND MATERIALS................................................................................................10
3.1. Study Area and Source of Data...........................................................................10
3.2. Method of data collection...................................................................................10
3.3. Sampling method................................................................................................11
3.4. Sample size determination..................................................................................12
3.5. Variables in the study..........................................................................................14
3.5.1. Dependent variable......................................................................................14
3.5.2. Independent variables..................................................................................14
3.6. Study design and analysis...................................................................................15
3.7. Descriptive method.............................................................................................16
3.8. Inferential method...............................................................................................16

II
 3.8.1. The chi-square method................................................................................16
3.8.2. Logistic regression.......................................................................................17
3.8.3. Odds Ratio...................................................................................................18
3.8.4. Parameter Estimation for Logistic Regression............................................19
3.9. Assessments of Model Adequacy.......................................................................20
3.9.1. The goodness of fit of the model.................................................................20
3.9.2. The Wald statistics.......................................................................................21
4. TIME SCHEDULE AND BUDGET BREAKDOWN...........................................................................22
4.1. TIME SCHEDULE.............................................................................................22
4.2. BUDJET CONSTRANT.....................................................................................22
Reference.......................................................................................................................23

III
Acronyms and Abbreviation
CPR = Contraception Prevalence Rate

Ho=null hypothesis

H1=alternative hypothesis

OR=odds ratio

UN = United Nation

WHO = World Health Organization

IV
 Executive Summary

The aim of research work is to apply Students theoretical achievement practically and
they can get more experience on decision making and problem solving professions. To
perform the given task computer packages like SPSS, Mini tab, Excel, and MS-word are
the main equipment. During this research work we used primary data, which had
collected from gimba town. From this data, we want to analyze and interpret the result by
using appropriate statistical method, like chi-square test of independence and logistic
regression analysis. Inferential statistics is a type of statistics which contains the method
of logistic regression analysis and chi-square test will be used as method of data
analysis. Descriptive statistics is a kind of statistics which describes the using different
measures like measures central tendency (MCT), dispersion, and various graphical and
diametrical presentation using table and charts like graphs & pie charts. By using chi-
square test of independence, we want to study the association between the variables.
From logistic regression analysis, we want to identify the most significant factors of
family planning users and also their relationship. From the result of data analysis and
interpretation some recommendation and conclusion would be drawn.

V
1. INTRODUCTION
1.1. Background of the Study

Family planning is essential in helping women and their male partners to decide freely on
whether to have children, how many to have, and when to do so. It improves both
maternal and child health, reduces the prevalence of unwanted pregnancies and unsafe
abortions, prevents sexually transmitted infections, and enhances economic well-being of
families(M. G. Anasel and U. J. Mlinga2014) . In fact, family planning also promotes
women’s sense of autonomy and their ability to make health decisions. As a result, the
United Nations (UN) has prioritized it to increase and sustain the utilization of family
planning because of its importance in the attainment of sustainable development goals. In
particular, emphasis has been put on universal access to a full range of safe and reliable
family planning methods to help couples realize their rights to freely and responsibly
decide the number and spacing of their children (U. Nations Department of Economic, S.
Affairs, and P. Division, “World Fertility and Family Planning 2020: Highlights.”).

According to the World Health Organization (WHO), almost 60% of women of

childbearing age use using family planning globally. Even though evidence shows a
global increase in the use of family planning, especially in Asia (62%) and Latin America
(67%), sub-Saharan Africa, inclusive, paints a different picture as there is average of less
than 20% month use of family planning. Furthermore, less than 30% of women of
childbearing age in sub-Saharan Africa are use family planning with more than 200
million women wishing to prevent unwanted pregnancies yet not using these services.
(UNFPA. (2021). State of World Population 2021)

Ethiopia being the second most populous nation in Africa, after Nigeria has been facing
multitudes of challenges following rapid population growth including environmental
degradation, chronic food insecurity, high maternal and child mortality rate. The total
fertility rate of Ethiopia is about 4.6 children per woman with contraceptive prevalence
rate (CPR) of 36% and an unmet need for FP of 22% for married women [6]and 24% for
total women of age (15–9) years[7]. If Ethiopia follows its current rate of growth, its

1
population will be doubled in the next 30 years, hitting 210 million by 2060 [6]. Most of
the world's population growth in the next, 40–50 years is expected to come from Africa
and Ethiopia will take a large share for this growth. This indicates that Ethiopia is among
countries with the highest total fertility rates in the world.
At present, contraceptive methods in Ethiopia, which is free of cost is provided in both
governmental and NGO health facilities including hospitals, clinics, health centers, and
health posts. But, Ethiopia is among countries with low contraceptive prevalence rate,
which is only 36% [3]. This resulted in high total fertility rate and unwanted pregnancy
which intern affects the maternal and child health status. Since, the country is a
multiethnic and multi-cultural, it needs to investigate prevalence of contraceptive use and
its predictors in the country. This is proposed by one of the previous studies, conducted
about contraceptive use, in specific areas of country.

1.2. Statement of the Problem

The use of family planning methods is a critical factor in promoting public health,
reducing maternal and child mortality, and enhancing the overall quality of life. Despite
the availability of various family planning methods, their adoption remains inconsistent
across different regions, communities, and demographic groups. In many countries,
especially in rural and underserved areas, the use of family planning services continues to
face significant barriers. These barriers may be influenced by a range of socio-economic,
cultural, educational, and healthcare system factors, which differ across population
subgroups.To understand the complexities of family planning adoption, it is essential to
identify the factors that affect its use and how these factors vary among different strata of
the population. These factors could include access to healthcare services, knowledge
about family planning, cultural attitudes, socioeconomic status, and education levels,
among others. However, these influencing factors are not uniformly distributed across
different groups, necessitating a more nuanced investigation that accounts for the
diversity within the population. (Cleland et al., 2012)

The objective of this study is to explore and identify the key factors affecting the use of
family planning, with a particular focus on how these factors differ across various

2
subgroups within the population. Using a stratified sampling design, this research will
segment the population into distinct strata based on variables such as age, marital status,
educational level, and income, to ensure a comprehensive understanding of the various
factors influencing family planning use across different demographic segments.

The use of family planning is a cornerstone of public health strategies aimed at reducing
maternal and child mortality, promoting reproductive health, and supporting sustainable
population growth. However, despite the proven benefits of family planning, its adoption
remains inconsistent across different demographic groups and regions. Various factors—
such as socio-economic conditions, cultural beliefs, access to healthcare services,
education, and geographic location—contribute to this variability in usage (Bongaarts,
2016; Sinding, 2009). These factors can be especially pronounced in low- and middle-
income countries, where barriers to family planning access and use are often more
complex.

The challenge lies in understanding how these factors affect family planning usage
differently across distinct population subgroups. For instance, women in rural areas may
face different challenges compared to those in urban centers; likewise, women with lower
levels of education may experience different barriers compared to those with higher
educational attainment (Cleland et al., 2012). Such variations necessitate a detailed,
stratified examination to identify specific determinants within distinct population strata.

Thus, the purpose of this study is to identify the factors that influence the use of family
planning in a heterogeneous population, with a particular emphasis on variations across
different strata. By using a stratified sampling design, this research will segment the
population based on variables such as age, marital status, education, socio-economic
status, and urban vs. rural residence. This approach allows for a more precise analysis of
how each factor influences family planning use in specific demographic groups,
providing a deeper understanding of the barriers and facilitators to its adoption.

The findings from this study could inform more tailored and effective interventions and
policies that address the unique needs of different subgroups, ultimately improving the

3
overall uptake of family planning methods and contributing to public health goals
(UNFPA, 2021).

The study would be mainly focused on the factor that affects use of family planning in
Gimba town, is the aimed to investigations the various problem by which use of family
planning is hindered. This activity mainly addressed such question: -
What factor affecting the use of family planning?
 Is the Age, Education, Religion, Marital Status, household of income, Occupation
of woman and Number of children having a significant effect on the using family
planning?
 Does finance as a problem contributing to family planning resulting to problem of
population control?
 Does religion belief discourage family planning?
 Is there any difference between unwanted pregnancy and frustration/pursuance of
money to population control?

1.3. OBJECTIVES

1.3.1. General Objective

The study's general objective is to determine factors affecting the use of family planning
in Gimba town.
1.3.2. Specific Objectives

To assess the impact of cultural and religious beliefs on the

acceptance and utilization of family planning services.

·To explore the barriers to the utilization of family planning methods, including
financial, social, and psychological factors.

·To assess the effectiveness of education and awareness campaigns in promoting

family planning usage.

4
  To assess the impact of cultural beliefs and religious practices on
individuals’ decisions to adopt or reject family planning methods in
[specific community].

 To identify and analyze the socio-demographic factors (such as age,

education level, income, marital status, and occupation) influencing
the use of family planning methods in [specific population or region].

 Assess the Impact of Socio-Economic Status on Family Planning

Utilization:**

 To understand how cultural beliefs and social norms influence family

planning practices and attitudes towards contraception.

Scope of the Study

The scope of this study is focused on understanding the factors that influence the use of
family planning methods in a specific geographic area, with an emphasis on identifying
how these factors vary across different demographic subgroups. This research will utilize
a stratified sampling design to ensure a comprehensive examination of factors affecting
family planning use among diverse population segments. The study will address both
individual and contextual factors that shape family planning decisions and usage,
including socio-economic, cultural, healthcare access, and policy-related
variables.Cleland, J., Harbison, S., & Shah, I. H. (2012).
The scope of study in a research proposal on "Factors Affecting the Use of Family Planning"
defines the boundaries within which your research will be conducted. It typically includes the
geographical area, target population, time frame, and specific aspects of family planning you will
focus on. Here’s how you could structure it:

5
1.4. Significance of the Study

Thefindingsobtainedfrom thisresearchcouldbeusefulinmanyways.

The study can help identify and address social and cultural
barriers that prevent individuals from using family planning
methods. By raising awareness and challenging misconceptions,
the research can contribute to more open and informed
discussions about family planning and reproductive health.

Family planning has significant implications for economic development. When individuals can
plan their families, they are better able to invest in education, career opportunities, and other
aspects of personal development. This can lead to improved economic outcomes not only for
individuals but also for societies as a whole.

 Effective family planning reduces the number of unintended pregnancies, which can
lead to a decrease in maternal and child mortality rates.
 Understanding and improving family planning can help manage population growth,
which has direct implications for public health and resource allocation.
 Family planning enables women to pursue education and employment opportunities,
contributing to economic growth and development.
 Access to and use of family planning is closely linked to the empowerment of
women, allowing them greater control over their reproductive health and life choices.
 When women can plan their pregnancies, they are more likely to achieve higher
educational levels and participate in the workforce, leading to better gender equality.

6
2. Literature Review
2.1. Theoretical literature

The use of family planning is influenced by a complex interplay of various factors,

including demographic, socioeconomic, cultural, religious, accessibility, affordability,
and government policies. Understanding these factors is crucial for policymakers and
healthcare providers to develop targeted interventions and programs that improve
reproductive health outcomes and promote the use of family planning in under serves
populations((Andi et al., 2014; Okigbo et al., 2017).
The use of family planning is not only influenced by practical and empirical factors, but
also by underlying theoretical frameworks that seek to explain human behavior and
decision-making in the context of reproductive health. Several theoretical models have
been developed to understand the factors that influence contraceptive use, including
individual, social, and institutional influences. Below is a brief discussion of some of the
key theoretical frameworks that help explain family planning behavior.(Murray, J.,
Othman, S., & Heymann, J. (2015).

Socioeconomic factors, such as income, education, employment status, and access to

healthcare, also impact the use of family planning. In low-income countries or regions
with limited access to healthcare, individuals may be less likely to access and use family
planning services due to financial constraints or lack of knowledge about available
options (World Health Organization, 2018).

Cultural and religious beliefs can significantly influence the use of family planning. In
some societies, there may be strong cultural norms or religious teachings that discourage
the use of contraception or limit family size. In these cases, individuals may be less likely
to use family planning methods, even if they are available and accessible (United
Nations, 2019).
Accessibility and affordability of family planning services are critical factors in their use.
In regions where family planning services are readily available and affordable,
individuals are more likely to access and use them. Conversely, in areas where there is

7
limited access to family planning services or where they are expensive, individuals may
be less likely to use them (World Health Organization, 2018).

Government policies and programs can also influence the use of family planning. In
countries where there are strong government policies promoting family planning and
providing access to services, there is often a higher prevalence of its use. Conversely, in
regions where there is limited government support for family planning, individuals may
be less likely to access and use these services (United Nations, 2019).

Education of the women

Female education is expected to influence women′s access to modern knowledge and new
ways of life and hence the extent to which they are familiar with stand approve of
contraception. Education also enhance know how to acquit and conform of behavior as
contraception′s. women′s education tends to break down barriers to communication about
contraception between spouses, so as they know about contraception between spouses, so
as they know more they use more contraception that others ( Cleland, J., Harbison, S., &
Shah, I. H. (2012)).

Financial Impact on Family Planning

When it comes to family planning, economic considerations play a significant role in

shaping decisions. The financial impact of having a child can be substantial, affecting
everything from household expenses to future career opportunities. Factors such as the
cost of raising a child, including healthcare, education, and daily living expenses, can
influence when and how many children a couple chooses to have. Additionally, economic
stability is often linked to access to contraceptives and family planning services, making
financial status a critical factor affecting these decisions. (Worku, S.A., Ahmed, S.M. and
Mulushewa, T.F., 2019.)

Physical And Mental Well-Being

It is essential to take into account the physical and mental health of individuals when
examining the factors that influence family planning. Physical health plays a pivotal role
in the ability to conceive and carry a baby to term. Factors such as a balanced diet,

8
regular exercise, and avoiding harmful substances like tobacco and alcohol all contribute
to enhancing fertility. (Worku, S.A., Ahmed, S.M. and Mulushewa, T.F., 2019.)

Age of the women

The age at which women have their first baby has an implication for birth rates and
population. There is some evidence that women have their first pregnancy in their teens
have more children on average than those who start their child bearing later; and they are
of course at risk of subsequent pregnancies for longer period (Cart Wright 1976:41).

Occupation of the women

Occupation of women can have an impact on the use of family planning. Women who
have demanding jobs or long working hours may be less likely to use family planning
methods due to concerns about their fertility or the impact on their careers. Additionally,
women who have limited access to family planning services or information may face
barriers in using them effectively.

women who work in physically demanding or high-stress jobs may be less likely to use
certain types of contraception, such as hormonal contraceptives, due to concerns about
their health or the potential impact on their fertility. Women who have limited access to
family planning services or information may also be less likely to use family planning
methods, as they may not have the necessary knowledge or resources to access them.
(United Nations. (2019). World Population Prospects 2019:)

Religion

The reproductive aspect of human beings is one of the attributes, which are affected by
religions belief, and value of society. The different types of religion don′t accept the use
of contraception. The total prevention of pregnancy is absolutely for bidden and
sanctioned by Muslim, Orthodox and other religions (WHO Family planning. 2015.)

Number of children large

share of agricultural work was done by women and children, even very young ones
perform numerous tasks in rural area. A man with many children can have his land

9
cleared for long follow cultivation by young sins and all or merely all other agricultural
work done by women and children. In addition children can be viewed as a form of
insurance for their parents, especially in time of old age. This condition affects the use of
family planning. (WHO Family planning. 2015).

2.2. Empirical literature

The use of family planning methods is influenced by a complex interplay of socio-

economic, cultural, healthcare, and policy factors. Numerous empirical studies have
explored these factors, offering valuable insights into why family planning uptake varies
across different populations and settings. Below is a brief discussion of some key
empirical findings related to factors affecting the use of family planning (Wulifan et al.,
2016; Adebowale et al., 2018)..

Numerous empirical studies have examined the various factors that influence the use of
family planning methods at the individual, household, community, and societal
levels.several studies have consistently found that age and education are significant
predictors of family planning use. Younger individuals, particularly those in their
reproductive years, are more likely to use contraceptive methods compared to older
individuals (Andi et al., 2014; Okigbo et al., 2017). Higher levels of education are also
associated with increased knowledge, positive attitudes, and greater utilization of family
planning services (Mekonnen & Worku, 2011; Kabagenyi et al., 2014).

Socioeconomic status, as measured by income and employment, has also been shown to
influence family planning use. Individuals with higher incomes and those who are
employed tend to have better access to and resources for family planning services,
leading to higher rates of contraceptive use (Wulifan et al., 2016; Adebowale et al.,
2018).

Household-level factors, such as spousal communication and decision-making, have been

identified as important determinants of family planning use. Studies have found that
when couples engage in open discussions and make joint decisions about family
planning, they are more likely to use contraceptive methods (Kabagenyi et al., 2014;
Okigbo et al., 2017).

10
 the availability, accessibility, and quality of family planning services have been shown
to impact their utilization. Communities with well-stocked clinics, trained healthcare
providers, and affordable services tend to have higher rates of family planning use
(Mekonnen & Worku, 2011; Wulifan et al., 2016).

Demographic factors, such as age, gender, marital status, and number of children, play a
significant role in the use of family planning. Younger individuals, particularly women,
are more likely to use family planning methods due to their reproductive potential.
Conversely, older individuals may be less likely to use family planning due to concerns
about their health or the health of their partners (United Nations, 2019).

Societal-level factors, such as national policies and legal frameworks, have also been
found to influence family planning practices. Studies have demonstrated that supportive
policies, comprehensive sex education, and the integration of family planning services
into the broader healthcare system can contribute to increased use of contraceptive
methods (Kabagenyi et al., 2014; Adebowale et al., 2018)

On the other hand, women from lower socio-economic backgrounds, especially in rural
areas, face significant barriers to family planning. These barriers include financial
constraints, limited access to healthcare services, and lack of information. Kebede and
Adamu (2014) found that women in low-income communities often prioritize immediate
household needs over family planning, and the cost of contraceptives can be prohibitive.
This is particularly true in sub-Saharan Africa, where financial barriers to accessing
modern contraceptive methods remain a major challenge.Sinding (2009) also found that
employment status and economic independence play a crucial role in women’s ability to
access and use family planning

. Employed women with a stable income were more likely to use contraception due to
greater autonomy in decision-making and improved access to healthcare services.Cultural
beliefs and social norms significantly influence family planning decisions. Studies show
that in many societies, particularly in developing countries, religious and cultural
attitudes toward contraception can either encourage or hinder its use. For example,
Fayomi and Idowu (2013) explored the role of cultural beliefs in Nigeria and found that

11
eligious doctrines, particularly in Muslim and Catholic co mmunities, often discourage the
use of contraception, perceiving it as contrary to religious teachings.Bongaarts (2016) also noted
that gender norms play a significant role in shaping family planning behavior. In patriarchal
societies, women may not have trhe autonomy to make independent decisions regarding
contraception, and their ability to access family planning services may be constrained by their
husbands’ or family members' approval.

Conceptual Framework:

Aconceptual framework serves as a visual or narrative representation of the key variables

and their relationships within a research study. It helps to outline the factors that are
believed to influence the use of family planning, providing a clear structure for
understanding how different elements may interact. The conceptual framework for the
topic "Factors Affecting the Use of Family Planning" will draw upon various theories,
models, and empirical findings that highlight the key determinants of family planning
behavior.(Cleland, J., Harbison, S., & Shah, I. H. (2012).

This conceptual framework suggests that family planning use is influenced by multiple
interrelated factors. Socio-economic factors such as income, education, and employment
significantly determine access to and adoption of family planning methods. Cultural and
social norms, including religious beliefs and gender roles, shape attitudes toward family
planning.(Sinding, S. W. (2009).

Below is a simple visual representation of the conceptual framework for understanding

the factors affecting the use of family planning:

Copy code

[ Socio-Economic Factors ] ↑ ↑

Income Level ──> Education Level ──> Employment Status ──>

Residence (Urban/Rural)

[ Cultural and Social Factors ] ↑ ↑

Religious Beliefs ──> Social Norms ──> Gender Norms

12
3. METHODOLOGY AND MATERIALS

3.1. Study Area and Source of Data

Gimba is found at the northern part of Ethiopia specially in the Amhara region.which
apart 484km from addiss Ababa, 362km from the capital city of Amhara region Bahirdar
and 79km from the capital city of south wollo zone Dessie. Tulu Awlia is a town in the
Gimba pasture area, Legambo woreda of South Wollo. It's located about 79km (49mi)
southwest of Dessie, 22km (13.7mi) northeast of Akesta, and 52km (32mi) south from
the town of Tenta. Elevation: 3,224m (10,577ft) above sea level.
The demographics of Gimba town census reported in 2017 a total population for Gimba
is 84562, of whom 41494 were men and 43068 were women. The photograph of the area
is mostly undulating the weather condition is Dega type. The income of people, who live
in that area are mostly depends on agricultural economy and marketing are commonly
produced cash crops is a staple food to the area. The total population of Gimba town
estimated 84562.
3.2. Studypopulation

3.2. Method of data collection

To conduct the study very well the data are obtained from primary source. Primary data
refers to the data that is collected by the investigator for the first time. Primary data
provides a first-hand account of the situation. The information obtained from primary
data is more reliable as the investigators collect the data by her self, she can take all
precautions to insure their reliability. We are also distributed the question for the
respondents randomly. Because there are some respondents who do not understand the
question by reading, So We are interpret the question for the respondents by face to face
talking with together. Questionnaire and Interviewing (face to face) method is a social
process that involves the interviewer and respondent.

Surveys or questionnaires are one of the most common methods for collecting primary
data. A structured questionnaire can be distributed to individuals who are either currently
using family planning methods or are in the target population. The survey can include

13
both closed-ended (e.g., yes/no, multiple choice) and open-ended questions to gather
quantitative and qualitative data.(( Creswell, J. W. (2014). Research Design.)

We are used these data collection method because some of the people who live in this
area are illiterate and most of the people don′t understand the idea of the question by
reading it.One-on-one interviews provide an opportunity for in-depth understanding of
individual perspectives. Interviews can be conducted with individuals who use family
planning methods, healthcare providers, or community leaders. Semi-structured
interviews allow the interviewer to explore responses in more detail, helping to uncover
personal experiences, social norms, and deeper insights into the factors influencing the
use of family planning.( Smith, J., & Elwood, L. (2018)

3.3. Sampling method

The method of sampling design is stratified sampling design.Stratified sampling is a

technique used in research to ensure that specific subgroups or strata within a population
are adequately represented in the sample. It is especially useful when the researcher
believes that the population is heterogeneous, meaning there are distinct subgroups
stratified sampling ensures that data is gathered from various segments of the population
in a way that reflects these divisions, which can improve the representativeness and
accuracy of the results.( Thompson, S. K. (2012). Sampling (3rd ed.). Wiley.)

The town is stratified in to some strata depending on their Kebele. In this case the strata
in town is Kebele 01tulu, Kebele 01 Chiro , Keble 014, Kebele 023, Kebele 024, Kebele
025, Kebele 026 dembesh, Kebele 026 yerma, Kebele 027and Kebele 029 in Gimba
town. Based on this allocation of Kebeles, from each stratum, sample is selected by
proportional allocation method to the size of strata (size of population in a given strata).

The sample size in each stratum is proportionally allocated as;

N- Total number of population Gimba town.

-population size in h stratum

14
 - Sample size drown from stratum

n ∗ Nℎ
Nh= (1)
N

Where n=n1+n2+n3+n4+n5+n6+n7+n8+n9+n10

Table-1 Shows Summary of population and sample size in each stratum.

Stratum Population
Stratum1= N1=total number of kebele 01 tulu=25928 N 1∗n
n1=
N
Stratum2= N2=total number of kebele 01 chero=5786 N 2∗n
n2=
N
Stratum3= N3=total number of kebele 014=5936 N 3∗n
n3=
N
Stratum4= N4=total number of kebele 023=7003 N 4∗n
n4=
N
Stratum5= N5=total number of kebele 024=6095 N 5∗n
n5=
N
Stratum6= N6=total number of kebele 025=4658 N 6∗n
n6=
N
Stratum7= N7=total number of kebele 026 dembesh=6928 N 7∗n
n7=
N
Stratum8= N8=total number of kebele 026 =8248 N 8∗ n
n8=
N
Stratum9= N9=total number of kebele 027=7885 N 9∗ n
n9=
N
Stratum10= N10=total number of kebele 029=6095 N 10 ∗ n
n10=
N
N=total number of population in Gimba town=84562

3.4. Sample size determination

Determining the sample size is Key on the overall statistical process. An appropriate
sample size is one of the mean of gaining high precision, accuracy and confidence with
minimum cost.sample size determination ensures the study has enough statistical power

15
to detect significant results while balancing cost, time, and feasibility. By considering
factors such as population variability, confidence level, margin of error, and effect size,
researchers can ensure that their study is well-powered to address the research questions
effectively(Thompson, S. K. (2012). Sampling (3rd ed.). Wiley.)

The sample to be used in which different design would produce different level of
precision for the same size or conversely different sample size for the same level of
precision. But remember that it is interested primarily in the accuracy.

α
no=(z )2pq,where no=the desired sample size.
2

Z= standard normal deviation usually set as 1.96(5%).

P =proportion of the target population estimated to have a particular characteristic. The

value of p is calculated from a pilot survey.

q=1-p

d=degree of accuracy desired,(marginal errors)

We know that N=population size

zα
no=( 2 )2pq (2)
2
d

zα no
2
no=( ) pq, n= no
2

2 1+
d N

nO no
>5 % ; n=
if N no
1+
N

no
if <5 % ; n=no
N

n= is the sample will be selected.

16
P=is the number of proportion ( Based on previous research proposal p=0.745 &q=1-
0.745=0.255 by (ABERA ASFAWU) in 2007 E.C. )

in Gimba town there is ten kebeles. A sample size for those Kebele would be determining
the formula& sample size estimation.

n ∗ Nℎ
nh=
N

Kebele Population size (Nh) Sample size (nh)

01 (Tulu) 45467 24
01 (Chiro) 5786 6
014 5936 6
023 7003 8
024 6095 7
025 4658 5
026 (Dembesh) 6928 7
026 (Yerma) 8248 9
027 7885 8
029 6095 7
Total 84562 91

We have N=84562 ,P=0.745 , q=1-p=1-0.745=0.255

α =0.05 and d=0.09

then we can calculate the total sample size as;

2p
( zα /2) (1 − q)
no= 2 = (1.96)2*0.745*0.255/(0.09)2=0.72981/0.0081=91
d

To determine the sample size from each kebeles, sample size will be used to stratify
sampling with proportional allocation.

17
3.5. Variables in the study
To do this, researchers need to consider various variables.variables are the key factors
that will be investigated to understand what influences the use of family planning
methods. These variables can include both independent variables (the factors that are
believed to influence the outcome) and dependent variables (the outcomes being
measured).( Cleland, J., & Ali, M. (2006).)

3.5.1. Dependent variable

The dependent variable is the outcome or result that is being measured. In this study, the
use of family planning is the outcome that the researcher is interested in understanding. It
is influenced by various factors.Using family planning method(0and1) 0=’’yes’’
1=’’no’’)

3.5.2. Independent variables

The independent variables are the factors that the researcher believes influence the
dependent variable. These are the "causes" or the factors affecting the use of family
planning methods.

These can include demographic factors, such as age, gender, and marital status; cultural
norms and values related to family size and childbearing; access to education and
healthcare services that can provide information about family planning options; economic
conditions, such as income and employment status; and government policies related to
family planning and reproductive rights.( Bongaarts, J. (2016).)

Independent variables categories

Educational level 0 illitrate

1 Elementary

2 Secondary&above

Religion 0 orthodox

1 muslim

2 other

18
 Martial status 0 married

1 single

2 divorce

3 widowed

Household income

Age of woman

Occupation of woman 0 employer

1 merchant

2 Daily labour

Number of children

contraciptive 0 3month

1 6month

2 other

pregenancy 0 yes

1 no

3.6. Study design and analysis

The study design defines the approach and structure of the research and helps ensure that the
study's objectives are addressed in a scientifically valid way.

The study design is a cross sectional design because It is ideal for studying the prevalence of
family planning use and the factors associated with it (such as education, income, age, etc.)
within a specific population at a specific point in time. A cross-sectional study collects data at a
single point in time. It is observational and provides a snapshot of the population's
characteristics and behaviors.( Cleland, J., & Ali, M. (2006).

19
3.7. Descriptive Statistics

The descriptive method in research refers to techniques that aim to describe and summarize
characteristics or phenomena without manipulating any variables. In the context of a study
titled "Factors Affecting the Use of Family Planning", the descriptive method would be used to
provide a comprehensive picture of how family planning is used, what factors are associated
with it, and the characteristics of individuals who use family planning versus those who do not. It
does not focus on cause-and-effect relationships but rather on understanding the "who,"
"what," "where," and "how" of the research topic.

Descriptive statistics is the process, which would be used in the study to analyze and summarize
mass of numerical data in to meaning full statistics techniques, like that of tabular
representation, pie chart and bar chart, and it is a collection, organization, summarization and
presentation of data in meaning full form by using different charts(Khan, M. E., & Mandal, R. K.
(2005).).

3.8. Inferential statistics

The inferential method in research is used to draw conclusions or make inferences about a
larger population based on a sample of data. Unlike descriptive methods, which focus on
summarizing and describing the data at hand, inferential methods allow researchers to test
hypotheses, estimate relationships, and make predictions based on the data collected. In a
study titled "Factors Affecting the Use of Family Planning", inferential methods are used to
understand the relationships between factors (such as education, income, age, and access to
healthcare) and the outcome of interest (the use of family planning methods).

Inferential is the objective of statistically decision making and prediction plays a very
important role in our individual lives. Therefore; the objective of statistics is to make
inference about a population based on information on a sample. To increase the accuracy
and feasibility of the study and to reduce load of the data can be analyzed by using the
most appropriate statistical software package such as SPSS Method.

3.8.1. The chi-square method

The Chi-Square (χ²) test is a statistical method used to assess whether there is a
significant association between two categorical variables. It is commonly used in
hypothesis testing to determine if the observed frequencies in a sample differ
significantly from the expected frequencies, based on a null hypothesis of no association.

20
The Chi-Square test is particularly useful for analyzing nominal data (i.e., data that can
be categorized without a natural order, such as gender, marital status, or the use of family
planning methods).( Agresti, A. (2018). Statistical Methods for the Social Sciences (5th ed.).
Pearson.)

Set up the hypothesis:

 Null Hypothesis (H₀): Assumes no association between the two categorical

variables (they are independent).
 Alternative Hypothesis (H₁): Assumes there is a significant association between
the two categorical variables (they are dependent).

At level of significance alpha (α)

Assumption:-

 The sample must be randomly selected from the population.

 The population must be normally distributed for the variable understudy.

 The observation must be independent of each other.

 The expected frequency for each category is at least 5. If there is a

category with all expected frequency of less than 5, either increase the
sample size or combine 2 or more categories make each expected
frequency at least 5.

Test statistics for the test of Independent

Let Oi r respect the observed number counts in the (Eij)cell and Eij represent expected
number of counts in the (ij) t cell. Then:-

2
x calculated=
k ∑ [ ( Oij − Eij )2 ]
∑ i=1 Eij
¿¿
i=1

Oij = the observed frequency

E I j =the expected frequency

The degrees of freedom (df) for the Chi-Square test is calculated as:

21
df=(r−1)(c−1)

where:

 r is the number of rows,

 c is the number of columns in the contingency table.

The calculated Chi-Square statistic is compared to the critical value from the Chi-Square
distribution table. If the statistic is greater than the critical value, the null hypothesis is rejected,
indicating a significant relationship between the variables.( Keller, G. (2011).)

3.8.2. Logistic regression

Logistic regression is a statistical method used to model the relationship between a

binary dependent variable (i.e., an outcome that has two possible outcomes, such as
yes/no, success/failure, or presence/absence) and one or more independent variables
(predictors). Unlike linear regression, which predicts a continuous outcome, logistic
regression is used when the outcome is categorical—specifically, when the dependent
variable is dichotomous.

In logistic regression, the goal is to predict the probability of a certain event occurring
based on the values of the independent variables. The model outputs a probability value
between 0 and 1, which can be converted to a binary outcome (e.g., "yes" or "no") based
on a threshold, typically 0.5.( Hosmer, D. W., & Lemeshow, S. (2000))

Assumption of Logistic Regression:-

Logistic regression is popular in part because it over come many of the restrictive
assumption of ordinals least square (OLS) regression. It assumption is as follows:

 The dependent variables need not be homo statistics for each level of independent
variables, which is no homogeneity of variance of assumption.

 Logistic regression assumes exclusions of all irrelevant variables and the

inclusion of all relevant variables in the model.

 Logistic regression does not require that the independent variable be continuous.

 Logistic regression does not assume a linear relationship between the dependent
variable and independent variables.

22
  Logistic regressions assume meaningful coding of the variables.

 Normally distributed errors terms are not assumed. Logistic regression does not
negative that independent variables be continuous.

 Logistic regression does not require that independent variables be unbounded.

The logistic regression model uses the logit function (the natural logarithm of the odds of the
dependent variable being 1) to model the relationship between the dependent variable and the
independent variables.( Agresti, A. (2018).) The formula for logistic regression is:

Denote the k predictors for binary response y by x 1, x2,,,,,,,,,,,,,,.XK the model for the log
odds is;

π (x)
Log it ((X))=Log(( ))=β0+β1X1+β2X2………………..+βkXk
1− π ( x )

Where βO is the model constant andβ1 ………………, βK arethe model parameters

ln is the natural logarithm,

3.8.3. Odds Ratio

The odds ratio (OR) is a statistic used to measure the strength of association between two
variables, typically in the context of a binary outcome (e.g., yes/no, success/failure,
presence/absence). It is widely used in logistic regression to quantify how the presence or
absence of a particular factor (predictor) affects the odds of a particular outcome happening.

The odds ratio compares the odds of an event occurring in one group with the odds of it
occurring in another group. Specifically, it is the ratio of the odds of an event occurring in the
presence of a predictor variable to the odds of the event occurring in the absence of that
predictor variable.( Hosmer, D. W., & Lemeshow, S. (2000).)

p
Odds= ………………………………………………………………………….
1− p

p1 p2
The odds of success are Odds1 = , and the odds of success equal in Odds2 =
1− p 1 1− p 2
.

23
The ratio of the odds from the two rows,

Odds1 P1 P2
Pi= = / …………………………………………………….is called
Odds2 1 − P 1 1− p 2
odds ratio.

Whereas the relative risk is a ratio of two probabilities, the odds ratio p i is a ratio of two
odds

3.8.4. Parameter Estimation for Logistic Regression

In logistic regression, parameter estimation refers to the process of determining the

values of the coefficients (parameters) that define the relationship between the
independent variables and the dependent binary outcome. The goal is to find the set of
parameters (β\betaβ) that best explains the data and allows for predicting the probability
of the binary outcome (e.g., success/failure, yes/no).

Logistic regression models the probability of a binary outcome, and the relationship
between the predictors and the outcome is expressed in the logistic function or logit
function.To estimate the parameters of logistic regression model, the two estimation
methods mostly used are maximum likelihood and non-iterative weighted least
squares method (Field, A. (2013)). When the assumption of normality of the predictors
does not hold, the non- iterative weighted least sq u estimation method is appropriate
for estimating the logistic model parameters due to this less restrictive nature of the
underlying assumptions (Field, A. (2013)). Thus in this study the maximum likelihood
estimation technique will be applied to estimate parameters of the model.
xiβ
e
Consider the logistic regression model P(x)= xiβ .
1+ e
Since observed values of Y say, Yi,s (i=1, 2,,,,,,, n) are independently distributed as
Bernoulli, the maximum likelihood function of Y is given by:

ares method is less efficient (Maddala, 1997). In contrast, the maximum likelihood
function of Y is given by;

( )
n n yi (1 − yi )
yi exi' β 1
L(β/y)=∏ p '
=¿ ∏ [ xi ] [ ] ¿……………………………………….
i=1 xi i=1 e ' β 1+ e xiβ

The objective of ML estimation is to get an estimator of which maximizes the likelihood

function expressed in equation (3.8). Since the likelihood equation is non- linear in the

24
parameters, the Newton-Raphson iterative maximum likelihood estimation method that
expresses β at the (u+1)th cycle of the iteration is given as:

Ḃu+1=Ḃu+(x’ẇu)^-1XRu…………………………………………

where u=1,2,3, ,,,,,,,,,,and ẇ is a diagonal matrix with its diagonal elements Pi’(1-Pi’) i.e.
ẇ=diag[pi(1-pi)=cov(y) . Finally,Ḃ is the maximum likelihood estimator of β with
residual R=pi-p(Hosmer, D. W., & Lemeshow, S. (2000).). Newton’s method usually
converges to the maximum of the log - likelihood in just a few iteration unless the data
are especially badly conditioned (Hosmer, D. W., & Lemeshow, S. (2000).).

3.9. Assessments of Model Adequacy

After the model is fitted the next important step is checking the model adequacy.
Assuming that we are preliminary satisfied with the final model (model contains
variables in their correct functional form) the objective will be to look at how closely
model fitted responses approximate observed responses. There are several steps involved
in assessing the appropriateness, adequacy and usefulness of the model. First, the overall
goodness of fit of the model is tested. Second, the importance of each of the explanatory
variables is assessed by carrying out statistical tests of the significance of the coefficients.

3.9.1. The goodness of fit of the model

In statistical modeling, goodness of fit refers to how well a model’s predictions match
the observed data. In the context of logistic regression, goodness of fit specifically
measures how well the logistic regression model describes the relationship between the
predictor variables and the binary outcome.

For logistic regression, the goal is to assess whether the model is a good representation of
the data or whether there are discrepancies between the predicted probabilities and the
observed outcomes. The model's goodness of fit is usually evaluated through various
statistical tests, diagnostic plots, and fit indices.

The goodness of fit or calibration of a model measures how well the model describes the
response variable. Assessing goodness of fit involves investigating how close values
predicted by the model are to the observed values.

Homer and Lemeshow (H_L) test:

25
It is used to partitioning the observation into ten equal side groups according to Homer-
Lemeshow predicted probabilities.

10
i.e Gh2=∑ ¿¿ 2 (Douglage. Moutgometry,2006).
j=1

Where, oj= observed number of cases in jthgroup (indicate 0,s & 1,s that are observed in
the dependent variable) & Ej= expected number of cases in j th group (predicted values of
the dependent variable based on the full logistic model). If H-L value is insignificance,
and there is no significance difference between the observed & expected values, then the
model is good fitted model.

Test of individual model parameters: The likelihood ratio test assesses the overall logistic
model but does not tell us if particular predictor variables are more important than others.
A non-significant likelihood ratio test indicates no difference between the full and the
reduced models, hence justifying dropping the given variable so as to have a more
parsimonious model that works just as well. Note that the likelihood ratio test of
individual parameters is a better criterion than the alternative Wald test when considering
which variables to drop from the logistic regression model.(Douglage.
Moutgometry,2006).

3.9.2. 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 lo-git coefficient is
zero).If the Wald test is not significant, then these explanatory variables can be omit from
the model(Agresti,1996)
Wald 2 statistics is used to test the significance of individual coefficients in the model
and is calculate as;

Ḃj 2
Z2=[ ¿
SE (Ḃ)

26
Each Wald statistics is compare with 2 distributions with 1 degree of freedom.Wald
statistics is easy to calculate but their reliability is questionable, particularly for small
samples.

27
4. RESULT AND DISCUSSION
ANALYSES AND INTERPRENTATION OF RESULTS.

4.1 ANALYSIS OF DESCRIPTIVE STATSITICS.

A type of statistically recommended data analysis that contains frequency graphs, tables
and charts as follows.

This chapter deals with analysis and interpretation of the primary data gathered stratified
randomly selected individuals.

Analysis and presentation were made by use of the information gathered from ninety one
(91) individuals with set of close ended questions.

Descriptive Statistics

N Minimum Maximum Mean Std. Deviation

ageofwoman 91 24 87 42.81 15.190

householdincome 91 2500 12500 6591.21 2305.614

childrennumber 91 0 8 2.93 2.169

According to descriptive statistics out put, we can say

 The average number of ageofwoman is 42.81 years with standard deviation 15.19
it can also be seen that mean of monthly income of household 6620.88 with
standard deviation 2305.285,and the mean of children number is 3.03 with
standard deviation 2.073.

 The minimum number of age of woman,monthly income and childrennumber is

24,2500 and 0 respectively.

 The maximum number of age of woman,monthly income and childrennumber is

87,12500 and 8 respectively.

28
 familyplanning

yes no total

Educational illitrate count 17 12 29

level
% of total 18.7% 13.2% 31.9%

elementary count 10 6 16

% of total 11% 6.6% 17.6%

Secondary&above count 31 15 46

% of total 34.1 16.5% 50.5%

total count 58 33 91

% of total 63.7% 36.3% 100%

Occupation of employer count 21 8 29

woman
% of total 23.1% 8.8% 31.9%

merchant count 24 13 37

% of total 26.4% 14.3% 40.7%

dailylabour count 13 12 25

% of total 14.3% 13.2% 27.5%

total count 58 33 91

% of total 63.7% 36.3% 100%

Martial status married count 31 22 53

% of total 34.1% 24.2% 58.2%

single count 11 1 12

% of total 12.1% 1.1% 13.2%

divorce count 10 6 16

29
 % of total 11% 6.6% 17.6%

widowed count 6 4 10

% of total 6.6% 4.4% 11%

total count 58 33 91

% of total 63.7% 36.3% 100%

contraceptive 3month count 37 5 42

% of total 40.7% 5.5% 46.2%

6month count 11 10 21

% of total 12.1% 11% 23.1%

other count 10 18 28

% of total 11% 19.8% 30.8%

total count 58 33 91

% of total 63.7% 36.3% 100%

religion orthodox count 18 9 27

% of total 19.8% 9.9% 29.7%

muslim count 29 12 41

% of total 31.9% 13.2% 45.1%

other count 11 12 23

% of total 12.1% 13.2% 25.3%

total count 58 33 91

% of total 93.7% 36.3% 100%

pregenancy yes count 27 8 35

% of total 29.7% 8.8% 38.5%

no count 31 25 56

% of total 34.1% 27.5% 61.5%

30
total count 58 33 91

% of total 63.7% 36.3% 100%

The table shows the frequency and percentage from the sample of 91s; hence 29(31.9%)
of the educational level were illitrate, 16(17.6%) were elementary and 46(50.5%) were
secondary and above which were included in the sample.The table also show that hence
17(18.7%) of the illtratei were use of family planning and 12(13.2%) were not use of
family planning.hence10(11%)of the elementary were use of familyplanning and
6(6.6%)were not use of family planning,hence 31(34.1%)of the secondary and above
were use of familyplanning and 15(16.5%)were not use of family planning.

When we come to occupation of woman from the total 91 samples29(31.9%)of them are
employer,37(40.7%)of them are merchant and the rest of them 25(27.5%) were daily
labour..The table also show that hence 21(23.1%) employers were use of familyplanning
and 8(8.8%)were not use of family planning,24(26.4%) merchants were use of
familyplanning and 13(14.3%)were not use of family planning and hence 13(14.3%)daily
labour were use of family planningand 12(13.2%)were not use of family planning.

The table also shows that the martialstatus of womans 53(58.2%) of the respondents were
married, 12(13.2%)of the respondents were single, 16(17.6%) of the respondents were
divorce and10(11%)of the respondents were widowed.The table also show that hence
31(34.1%)married were use of familyplanningand 22(24.2%)were not use of family
planning, 11(12.1%)single were use of familyplanning and 1(1.1%)were not use of
family planning,10(11%)of divorce were use of familyplanning and 6(6.6%)were not use
of family planning,6(6.6%)of widowed were use of familyplanningand 4(4.4%)were not
use of family planning.and also the total martialstatus of womans 58(63.7%) of the
respondents were use of familyplanning and 33(36.3%)of the respondents were not use
of familyplanning.

From the table above the contraciptive of woman 42(46.2%)of the respondents were
3month,21(23.1%)of the respondents were 6month and 28(30.8)of the respondents were

31
others.and hence 37(40.7%)of 3month were use of familyplanningand 5(5.5%) of the
respondents were not use of family planning,11(12.1%)of 6month were use of
familyplanning and 10(11%)of the respondents were not use of family
planning,10(11%)of others were use of familyplanning and18(19.8%)f the respondents
were not use of family planning.

From the table above 27(29.7%)of them are orthodox,41(45.1%)of them are muslim and
23(25.3%)of them are others and hence 18(19.8%)of orthodox were use of family
planning and 9(9.9%)of the respondents were not use of family,29(31.9%)of muslim
were use of familyplanning and 12(13.2%))of the respondents were not use of familyand
11(12.1%)of others were use of familyplanning and 12(13.2%)of the respondents were
not use of family which were included in the sample.When we come to the pregenancy
35(38.5%)of them are pregenancy and 56(61.5%)of them are no pregenancy.

Fig 4.1 The frequency pie chart representation of the respondent occupation of
women,there40.66% are merchant,31.87%are employer and 27.47% of occupation are
daily labour.

32
Fig From above pie chart of religion there 45.05% are muslim,29.67% are ortodox
and25.27% are others.

From the above pie chart of the respondent martial status of womean there
58.24%married,17.58%of martial status are divorce,13.19%single and10.99% of martial
status are widowed.

33
4.2 Analysis of inferential statistics

4.2.1 Chi-square test of association

Inferential statistics is statistical method deals with making inference or
conclusion about population based on data obtained from alimited number of
observation that come from the population.

HO: there is no association between dependent and corresponding independent variables

Versus
H1: there is association between dependent and independent variables (dependent).
Where, dependent variable is using family planning.
Independent variables are: level of education, religion, marital status , age ,
occupation ,pregenancy,contraciptive, number of children and income.
Reject HO if p-value<α (0.05)

Table 4.3 chi-square values of dependent variable with corresponding independent variables.
Dependent vs independent Pearson chi- Df Asymp.sig(2sided)
square

Family planning vs marital 4.752a 3 0.191

status

Family planning vs religion 3.487a 2 0.175

Family planning vs 21.466a 2 0.000

contraciptive

Family planning vs 2.455a 2 0.293

occupation

Family planning vs number 42.359a 8 0.000

of children

Family planning vs 0.605a 2 0.739

educational level

Family planning vs income 29.903a 34 0.669

Family planning vs age 48.136a 37 0.104

34
Family planning vs 4.423a 1 0.035
pregenancy

At 5% level of significance, the p-value is 0.191which is greater than the level 0.05. So
we fail to reject null hypothesis /we have no enough evidence to reject null hypothesis /
and conclude that there is no statistically association between marital status and family
planning Similarly, according to the result, at 5% level of significance religion,
occupation,educational level,income,age and family planning have no relation
(association) that is, they are independent.
At5%level of significance, the p-value is 0.000 which is less than the level 0.05. So we
reject null hypothesis /we have enough evidence to reject null hypothesis/ and conclude
that there is statistically association between contraciptive of the respondents and family
planning Similarly, according to the result, at 5% level of significance number of children
of the respondents, pregenancy of the respondents, and family planning have a relation
(association) that is they are dependent.

4.2.2 Analysis of logistic regression and odds

We consider the general logistic regression model with multiple explanatory variables.
Denote the k predictors for a binary response y by x1, x2,………….,xk. The model for the
log odds is log it{p(y=1)} =α+β1x1+β2x2+………..+ βkxk. Where y=1, user of family plan.

35
Likelihood ratio test

Ho: All coefficient of the model are zero

H1: At least one coefficient is different from zero

.α=0.05

Omnibus Tests of Model Coefficients

Chi-square df Sig.

Step 1 Step 55.075 15 .000

Block 55.075 15 .000

Model 55.075 15 .000

Since the above omnibus test of model coefficient is on step 1, enter all the variables in
the model. The coefficient here gives as a measure of how well the model fits. It is the
null hypothesis states that information about the independent variables does not allow us
to make better prediction of the dependent variable. Therefore we would want that this
chi-squared value is significant. In this case the chi-square is significant and interpreted
us the model fits well.
Hosmer and Lemeshow Test

Step Chi-square df Sig.

1 9.180 8 .327

Hypothsis
H0; the model is good fit

Ha; the model is not good fit

The Hosmer Lemeshow statistic has chi-square value of 9.180 and a significance of
0.327, which means that Hosmer-Lemeshow test is not statistically significant and
therefore our model is quite a good fit. Because p-value exceeds level of significance
(α=0.05), that show there no significant difference between the observed and predicted
model values and hence the model fits. .

36
 Variables in the Equation

95% C.I.for
EXP(B)

B S.E. Wald df Sig. Exp(B) Lower Upper

Step ageofwoman -.028 .046 .378 1 .539 .972 .888 1.064

a
1
householdincome .000 .000 .034 1 .854 1.000 1.000 1.001

educationallevel 5.738 2 .057

educationallevel(1) -2.433 1.090 4.985 1 .026 .088 .010 .743

educationallevel(2) .836 1.269 .434 1 .510 2.308 .192 27.750

childrennumber 1.117 .352 10.063 1 .002 3.055 1.532 6.090

occupationofwoman .555 2 .758

occupationofwoman(1) -.714 .977 .534 1 .465 .490 .072 3.320

occupationofwoman(2) -.201 .793 .064 1 .800 .818 .173 3.871

maritalstatusofwoman 5.148 3 .161

maritalstatusofwoman(1 1.443 1.104 1.708 1 .191 4.232 .486 36.818

)

maritalstatusofwoman(2 1.815 2.029 .800 1 .371 6.144 .115 327.992

)

maritalstatusofwoman(3 -.646 1.182 .298 1 .585 .524 .052 5.323

)

contraceptive 11.582 2 .003

contraceptive(1) -1.365 1.368 .997 1 .318 .255 .017 3.725

contraceptive(2) 2.401 1.415 2.878 1 .090 11.031 .689 176.725

religion 6.132 2 .047

religion(1) -2.493 1.193 4.363 1 .037 .083 .008 .858

37
 religion(2) -2.672 1.100 5.900 1 .015 .069 .008 .597

pregenancy(1) -1.287 1.151 1.250 1 .264 .276 .029 2.636

Constant -.905 3.102 .085 1 .770 .404

a. Variable(s) entered on step 1: ageofwoman, householdincome, educationallevel, childrennumber,

occupationofwoman, maritalstatusofwoman, contraceptive, religion, pregenancy.

From the above variable equations educational level(1),

religion,religion(1),religion(2),children number and contraciptive aresignificant and the
remained variables are not significant.

Test of statistics in the inferential part of data analysis in the logistic

regression:

The fitted models is

Legit (p(y=1)} = βo+β1X1+β2X2+β3X3+β4X4+β5X5+β6X6+β7X7

Legit(p(y=1)}=-0.905-0.28(age)-2.433(educationallevel)+1.117(children number)
+1.443(martial status)+2.401(contraciptive)-2.493(religion)

From the output of the spss the educational leve with the reference categories
1(elementary) has the p-value 0.026 indicates that it is factor s those affects the family
planning. The children number has the p-value 0.002 indicates that it is factor s those
affects the familyplanning. Martial status with reference categories 0(married)has the p-
value 0.161 indicates that it is not factor s those affects the family planning.and the
Martial status with reference categories1(single) has the p-value0.191 indicates that it is
not factor s those affects the family planning and Martial status with reference categories
2(divorce),3(widowed) has the p-value0.371,0.585 indicates that it is not factor s those
affects the family planning respectively.

The contraciptive with the reference categories 0(3month) has the p-value 0.003
indicates that it is factor s those affects the familyplanning and The contraciptive with
the reference categories1(6month),2(other)has the p-value0.318,0.09 indicates that it is
not factor s those affects the family planning respectively.

38
Similarly with the above interpretation The religion with the reference
categories0(orthodox) has the p-value 0.047 indicates that it is factor s those affects the
familyplanning and The religion with the reference categories1(muslim) has the p-value
0.037 indicates that it is factor s those affects the familyplanning and the religion with the
reference 2(other)has the p-value 0.015 indicates that it is factor s those affects the
familyplanning.

The odds ratio interpretation

βo+β1X1+β2X2+β3X3+β4X4+β5X5+β6X6))

Exp((-0.905-0.28X1+2.433X2+1.117X3+1.443X4+2.401X5-2.493X6))

Based on the above spas output we can interprets as follows.

The odd ratio of educationallevel (1) deciding family planning that has factors on the
respondents are Exp (B)=0.088 times higher elementary than secondary&above. The
odds ratio of religion (1)deciding family planning that has factors on the respondents are
Exp(B) =0.083 times higher for muslim than others. The odds ratio of religion
(2)deciding family planning that has factors on the respondent are Exp(B)=0.69times.

Hypothesis test steps

Test the affect of educational level on the family planning

Step1 Ho: β2=0 vs. H1: β2#0

Step2 α =0.05

Step3 test statistics with the p-value i. e p=0.026

Step 4 decision, p-value <α=0.05 reject the null hypothesis

Step5 conclusion: we conclude that educational level of the respondent is highly affected
on the using family planning.

In similarly depend on the above p- value we can conclude that , education of the
respondent, religion of the respondent, contraceptive of the respondents on family
planning have highly affect on the using of family planning.

39
Wald test

Test the affect of religion(1) on the family planning

Step1 Ho: β2=0 vs. H1: β2#0

Step2 α =0.05

Step3 test statistics with the p-value i. e p=0.037

Step 4 decision, p-value <α=0.05 reject the null hypothesis

Step5 conclusion: we conclude that religion(1) of the respondent is highly affected on the
using family planning.

In similarly depend on the above p- value we can conclude that , education of the
respondent, contraceptive of the respondents on family planning have highly affect on
the using of family planning

Model summary for the relationship between family planning and independent variable.

Model Summary

Cox & Snell R Nagelkerke R

Step -2 Log likelihood Square Square

1 64.120a .454 .622

From the above table the value of cox & snell R 2 is 0.454.which is found between 0 and
0.75,this indicates that the logistic regression model fits the data.Also the nagelkerker R
square is 0.622 which is found between 0 and 1 which indicates the model fits the
data.From cox & snell R2 45.4% of the varation in the dependent variable is explained by

the predictor variable and nagelkerker R square shows that 62.2% of in the dependent
variable is explained by the explanatory variables.
CHAPTER FIVE

5.1 Conclusion
 As mentioned in the main objective of this study is to determine factors affecting
family planning. From findings and interpretation obtained in chapter -4 we
conclude as follows. From our research result there is highly association between

40
 education and family planning. From this we conclude that the more educated
respondents are more use of family planning services. Because if the respondents
are educated they simply choose the best contraceptive method regarding with
their health status and also they know the right time to use the contraceptive.
Therefore family planning had a direct relationship with religionof the
respondents. Regarding the respondent’s income and its relation with practice of
family planning there was no relation between them.

 From our research results there is a relationship between marital status of women
and family planning. That is protestant of people highly use family planning
service than orthodox and and muslim of the respondents. We generalized that
religion of the respondents affect the use of family planning service.

 In the above results there is association between contraciptive of respondents and

family planning.

 From the inferential analysis of the logistic regression we conclude that education
level ,religion and contraceptives are the factors that affect the family planning or
they are significant factors.

5.2 RECOMMENDATION
Depending on the outcome of the study we recommend the following:

 Increase Education and Awareness

 Improve Access to Contraceptives

 To increase the people access for contraception methods, the expansion of health
center, clinics, hospitals, etc with their worker should be necessary.

 To increase participation of the respondents towards family planning, appropriate

family planning program should be designed to reach all respondents with different
educational status.

 Government shall ensure to those respondents the right to have easy access to basic
health care facilities, information and education about family planning.

41
 The mass media should be given attention in the provision of better family planning
education since it is the major source of knowledge especially to those home bounded
women.

 Government should develop working with other NGO in this program because the
problem is serious in our country.

 Government should have included family planning programs in education curriculum

and trained health workers.

 We would like to inform that there are some variables not significant, then we inform
that the other researcher would dig out this problems to solve the family planning in
gimba towen.

TIME SCHEDULE AND BUDGET BREAKDOWN

4.1. TIME SCHEDULE

No Activities Time Needed(weeks)

1 Title selection 1 week
2 Proposal writing 1week
3 accepting comment and review 1 weeks
4 Data collection, analysis and processing 2 week

5 Summarizing and preparation of final draft 1 week

6 Submission of final draft 1 week

7 Final presentation 1 weeks
total 8 weeks

4.2. BUDJET CONSTRANT

Financial distribution for each activity is shown in the following table.

No. cases Quantity Price(birr)

1 Questionnaire paper 91 184

42
 2 Flash 1 550

3 Pen 3 75

4 Tea and coffee 15 150

5 Print 4 160

6 Mobile card 2 100

7 Reader 1 80

Total 1299

Reference
[1] M. G. Anasel and U. J. Mlinga, “Determinants of contraceptive use among married women in
Tanzania: Policy implication Résumé multinomiale et Binaire,” 2014. [Online]. Available:
http://aps.journals.ac.za978

[2] G. Mustafa et al., “Family Planning Knowledge, Attitudes, and Practices among Married Men
and Women in Rural Areas of Pakistan: Findings from a Qualitative Need Assessment Study,” Int
J Reprod Med, vol. 2015, pp. 1–8, 2015, doi: 10.1155/2015/190520.

[3] A. I. Mahadeen, A. O. Khalil, A. M. Hamdan-Mansour, T. Sato, and A. Imoto, “3 The Integrating

Health and Empowerment of Women in the South Region Project,” 2012.

[4] U. Nations Department of Economic, S. Affairs, and P. Division, “World Fertility and Family
Planning 2020: Highlights.”

[5] P. N. Tolefac, T. N. Nana, E. V. Yeika, N. S. Awungafac, Y. Ntsama, and P. N. Njotang, “Trends

and patterns of family planning methods used among women attending family planning clinic in a
rural setting in sub-Sahara Africa: The case of Mbalmayo District Hospital, Cameroon,” BMC
Res Notes, vol. 11, no. 1, Aug. 2018, doi: 10.1186/s13104-018-3658-1.

[6] “PMA2020-Ethiopia-R1-FP-indicator details”.

[7] “Ethiopia Demographic and Health Survey,” 2016.

43
[8] M. Abdulai et al., “Demographic and socio-cultural factors influencing contraceptive uptake
among women of reproductive age in tamale metropolis, northern region, Ghana,” Ghana Med J,
vol. 54, no. 2, pp. 64–72, Aug. 2020, doi: 10.4314/GMJ.V54I2S.11.

[9] T. T. Dasa, T. W. Kassie, A. A. Roba, E. B. Wakwoya, and H. U. Kelel, “Factors associated with
long-acting family planning service utilization in Ethiopia: a systematic review and meta-
analysis,” Contracept Reprod Med, vol. 4, no. 1, Dec. 2019, doi: 10.1186/s40834-019-0095-z.

References

 Bongaarts, J. (2016). The Effect of Family Planning Programs on Fertility in Developing

Countries. Population Studies, 70(3), 355-370.
 Cleland, J., Harbison, S., & Shah, I. H. (2012). Unmet Need for Family Planning and
Fertility Control in Developing Countries. Population and Development Review, 38(1), 1-
33.
 Sinding, S. W. (2009). Population, Poverty, and Family Planning: A Review of the
Evidence. Studies in Family Planning, 40(2), 57-62.
 UNFPA. (2021). State of World Population 2021: My Body is My Own. United Nations
Population Fund.

44