You are on page 1of 126

Basic Tips and Components of a research

proposal
2.1 Basic Tips in writing a research proposal
1.1 The need for a focus (think what you want to do & write it )
1.2 Starting where you are (interest matters most and helps to
tackle challenges )
1.3 Researching the background (every research is rooted in
an academic discipline, theories and methods)
 Good to have a thorough and up to date understanding of
the literature, background knowledge of the relevant
discipline, technical proficiency…..
 This just serves as a background but not necessarily
guarantee a sufficient starting point to design the research
1.4 Acknowledging the constraints
 real world enquiries face real world constraints
 The choice of research focus, allocation of time and
resources must be realistic
1.5 Defining the research problem
 The problem might be known but should be
scientifically defined (Scientifically & explicitly)
2.2 Components of a research proposal
1. Introduction
 A research proposal should start with an introduction written based
on review of related literature
Background or introduction may include;
o An overview of the main area under study;
o A historical perspective (developmental, growth, etc)
pertinent to the study area
o Philosophical or ideological issues relating to the topic
o Trends in terms of prevalence, if appropriate;
o Major theories; if any;
o The main issues, problems and advances in the subject area
under study;
o Important theoretical and practical issues relating to the
central problem under study;
o The main findings relating to the core issue(s)
2. Statement of the problem
 Identifying the gap in the existing body of knowledge
 Involves identification of some of the unanswered research questions and the
research questions for the current study
Major issues to be addressed;
o Identify the issues that are the basis of your study
o Specify the various aspects or perspectives on these issues
o Identify the main gaps, if there is any in the existing body of
knowledge
o Raise some of the main research questions that you want to answer
through your study
o Identify what knowledge is available concerning your questions,
specifying the difference of opinions in the literature regarding these
questions if differences exist
o Develop a rationale for your study with particular reference to how
your study will fill the identified gaps
Interest, relevance, measurement concepts, data availability, level of expertise
(has to be taken in to account in framing a RP)
3. Research questions/problem?
 Some researchers focus on research problem while
others emphasize research question
 However basically a problem that needs solution can
be framed in to questions and questions that need
answer can be framed in to problems
 Research questions are central to the research since
the whole purpose of conducting the research is to find
valid answers to them
 Developing a hypothesis is also very important to
further clarify the problem specifically for experimental
study
Q-1 Does quality of text books impacts on students
level of understanding the subject matter of
civics?

Q-2 What impacts does Teachers qualification on


the subject matter of civics may have on students
interest towards learning the subject?

Q- 3 Does the degree of corruption impact on the


stability of a political system?
A hypothesis is a statement of your assumptions about
the prevalence of a phenomenon or about a
relationship between two variables that you plan to
test within the framework of the study.
Considerations in building a hypothesis
 A hypothesis should be simple, specific and
conceptually clear.
 A hypothesis should be capable of verification
 A hypothesis should be related to the existing body of
knowledge.
 A hypothesis should be operationalisable or the
variables should be measurable
H1- Low quality text books may have led to poor
students level of understanding of the subject
matter of Development theories

H2 - Teachers qualification in the subject matter


may contribute in enhancing students interest
towards learning Research methodology

H3- High degree of corruption may lead to political


instability
 In building a hypothesis we have to establish
relationship among variables
Types of variables
• Independent Variable- the cause supposed to be
responsible for bringing about change(s) in a
phenomenon or situation.
• Dependent Variable-the outcome of the change(s)
brought about by introduction of an independent
variable
• Extraneous Variable-Several other factors operating in a
real life situation may affect changes in the dependent
variable
• Intervening Variable (confounding variable) links the
independent and dependent variables
Objectives of the study
 The goals a researcher set out to attain in his/her study
 Could be broadly classified as specific and general
 the general objective provides a short statement of the
scientific goal being pursued by the research while the
specific goal is operational in nature
 objectives of the study should be clearly stated and
specific in nature each of them addressing a specific
issue
 Use action-oriented verbs such as ‘to determine’, ‘to find
out’ and ‘to ascertain’, ‘to examine’, ‘to explaian’, ‘to
analyze’ etc…in formulating specific objectives
Example:
Suppose a researcher is investigating the impact of
immigration on the family,
General objective: To examine the impact of immigration
on the family
Specific objectives:
 To determine the impact of immigration on
husband/wife roles as perceived by immigrants
 To ascertain perceived changes in parental expectations
of children’s academic and professional achievement
 Examine the economic impact of immigration on the
family
 Show the impact of parents migration on children’s
educational performance
Research objectives should be;
• Precise
• Measurable
• Specific
• Functional
• Appropriate
• Achievable
• Realistic
The Literature review
 Is one of the most important component of the
research process and useful from the beginning to the
end
In reviewing the literature the researcher should be
concerned with;
 What literature is relevant to the research?
 What is the relationship of the proposed study to its
relevant literature
 How will the proposed study deal with the literature? In
particular, how will the argument in the proposal use
the literature?
Reviewing related literature helps to;
 Brings clarity and focus to the research problem
 Improves the methodology
 Broaden the knowledge base in the research area
 Contextualize the findings (placing your findings in to
the existing body of knowledge)
Procedures for reviewing the literature;
 The literature review can be used to narrow down the
focus area of the research problem and once the
problem is known the literature focuses on the
particular problem identified
The procedures include;
A. Search for existing literature in the area (After having
some idea on the broader subject)
 involves the search for books, journals etc..
B. Review the literature selected
 A good literature review is more than the summary of
the related literature
 Researchers are required to synthesize the literature
they are reading
 Build an argument out of it
 Critically examine it for its generalizability and
applicability
In reviewing the literature researchers are advised
to avoid;
 excessive quotation
 Too much reliance on secondary sources (Refer the
original sources of ideas)
 Attempting to report every thing you know or have read
Develop the theoretical and conceptual framework
 The function of theory in research is to identify the
starting point of the research problem and to establish
vision to which the problem is directed
 it determines and defines the focus and goal of the
research problem
 A theory provides a point of focus for identifying the
unknown in specific area
Theoretical framework
 A framework is described as the abstract and logical
structure of meaning that guides development of a
study
 All frameworks are based on the identification of
concepts and the relationship among those
concepts
 if relationship is found between two or more
variables theory should be formulated to explain
why the relationship exists
A theoretical framework can be defined as;
 An explanation of a phenomenon or an abstract
generalization that systematically explains the
relationship among given phenomena, for purposes of
explaining, predicting and controlling such phenomena
• A theoretical framework consists of theories that seem
to be interrelated
• the explanation concerns the relationship between
two or more variables or phenomena
• More formal and used for studies based on existing
theories
• Derived from specific concepts and propositions that
are induced or deduced
Purposes of theoretical framework
• To test theories
• To make research findings meaningful and
generalizable
• To establish orderly connections between
observations and facts
• To predict and control situations
• to stimulate research
Conceptual framework
 The conceptual framework stems from the theoretical
framework
 Consists of concepts that are placed within a logical and
sequential design
 It concentrates on one section of that theoretical
framework which becomes the basis of the study
 is an outcome of theoretical discussion, identification of
variables and showing inter relationship among them
 A theoretical framework can be easily depicted using a
diagram
Research Design
 What strategy will be followed? Within what framework?
From whom will the data be collected? How will the data
be collected? How will the data be analyzed?
 Responding to such questions will lead to designing the
research
Research strategy
 The research strategy refers to the set of ideas, by which
the study intends to proceed in order to answer its
research questions
 For instance, the strategy to be followed may be broadly
differ in terms of whether the research follows
qualitative or quantitative approach
 For each and every possibility (quantitative, qualitative
or mixed approach) the research has to put clear
strategy how to go about it
 by this the proposal will be able to indicate the basic
strategy behind the research

Sampling
 Determines from whom the data will be collected?
 The proposal should communicate the sampling
strategy, how big the sample will be and how it will be
selected
 Description of the sampling plan should include
justification of the sample size since there are well
established methods of sample size determination
Data collection instruments and procedures
 Selection of instruments and procedures for data
collection is also affected by whether we are pursuing
qualitative or quantitative method
 The instruments/tools for data collection may include;
 questionnaire, standardized measuring instruments, ad hoc
rating scales or observation schedules for quantitative
research
 questionnaire for a qualitative survey, where open-ended
questions are involved, or the schedule for qualitative
interviews, documents, diaries and journals, audiovisual
material or artifact
 Data collection procedures refer to the actual process
of data collection whatever instrument is proposed.
 So it refers to how the instruments are administered?
 For instance, if a questionnaire is to be administered
how?
 face-to-face? One-to-one or group administration? By mail? By
telephone?
 If interviews are involved how?
 where will the interviews be conducted (at the office? at
home? Somewhere else?) How will the recording be
done (by taking notes? by reconstruction after the
interview? by tape recorder?)?
 If observation is involved, is it overt or covert?
Data analysis
 How will the data be analyzed?
 what will be done with the data once they have been
collected. What methods of analysis will be used?
Ethical issues
 academic institutions are careful about any ethical
issues that research may have.
 To deal with them, all institutions have some form of
policy on ethics.
 A researcher needs to identify relevant ethical issues,
and describe how to deal with them in the proposal
 Such issues has to be looked at from the view point of
the respondent
Unit III- Research Design and Techniques
of sampling
3.1 Meaning and function of Research Design
 After defining the problem and indicting the research
questions, objectives and set the hypotheses; the
researcher should develop the most valid and reliable
method to gather and analyze data
 The researcher decides; the methods of data collection,
the instruments to be used, the sampling technique &
size, the time frame of the research, how the study
population is communicated etc…
 The reliability and validity of the findings is determined
on the basis of the quality of the methods employed
A research design can be defined as;
‘‘ A program that guides the investigator in the process of
collecting, analyzing and interpreting observations (data). It is
a logical model of proof that allows the researcher to draw
inferences concerning causal relation among variables.’’
‘‘ a blue print or detailed plan for how a research study is to be
completed – operationalizing variables so that they can be
measured, selecting a sample of interest to study, collecting
data to be used as a basis for testing hypothesis & analyzing
the results.’’
 Preparing a research design involves selection of appropriate
method of data collection ensuring the representativeness of
the sample selected, the validity of instruments developed
The study design involves decisions about;
 The study design to be employed (qualitative Vs
quantitative, cross sectional, longitudinal, survey, case
study etc.. )
 Determine the study population, the sampling
procedures, the methods, instruments and procedures
of data collection
3.2 Types of study design
Based on the frequency of contact with the study
population.
 Cross sectional
 the pre and post study design
 Longitudinal design
Based on the type of investigation
Post test only design (Experimental designs)
 Post test only design
 Pretest post test design
 Pretest post test control group design
 Post test only control group design
Case study, Survey
Based on frequency of contact with the study population;
A. Cross sectional study design
 The most common research in social sciences
 A one shot study where the researcher collects and
analyzes data and concludes the findings at one point
in time on a particular issue on a study population
 the investigation of the study population is carried out
only once to study a particular phenomenon as it
takes place during the time of the study.
 is less applicable when there is a need to study
changes in the issues or the phenomena under
investigation within the study population
B. The pre and post study design
 composed of two cross sectional study conducted on
the same study population to measure any pattern of
change in the phenomena under investigation after
some time.
 This design helps you to investigate changes effected
as a result of a particular intervention on a community
Eg. Awareness raising program on family planning
C. Longitudinal Study Design
 Time series analysis of the phenomena under
investigation
 Allows frequent contact with the study population for a
long period Eg. Polio vaccination program by the WHO
Designs based on the type of investigation
 relates to experimental and quasi experimental design
 helps to determine cause and effect relationships
between variables
 Experimental design may have such elements as
experimental group, control group, post-test, pre-test,
random assignment, comparison, manipulation etc…
Eg. Effect of drinking coffee on heart beat
A. Post test only design:
 investigate impacts of a program or intervention
already conducted on a community.
 No base line information is collected to assess the pre
intervention situation
 depends on respondents’ opinion of the situation
before the intervention or existing records
 Change is analyzed by comparing the baseline data with
the data from the post intervention period
 full investigation of only the post intervention period
 Difficult to assert that the change is occurred because
of the intervention
Eg. Teaching parents for children’s enrollment
B. Pre test-post-test design
 investigation is conducted before the intervention to
asses the situation and another investigation after the
intervention.
 The impact of the intervention is measured by
comparing data obtained in the two periods.
 it still lacks mechanisms to ensure whether the changes
occurred in the post intervention period are only
because of the intervention
 Hence the use of control and experimental group.
C. Pretest-post test control group design
 the researcher selects two population group one is
called as the control group and the other is an
experimental group
 This helps to conclude that, the changes occurred after
the intervention is resulted from it.
Non experimental designs
Survey design
 a survey is used as a design “for gathering
information about the characteristics, actions, or
opinions of a large group of people”
 Surveys can also be used to assess needs, evaluate
demand, and examine impact
 survey research is used to quantitatively describe
specific aspects of a given population.
 survey research uses a selected portion of the
population from which the findings can later be
generalized back to the population.
 Surveys are capable of obtaining information from
large samples of the population.
 inclusive in the types and number of variables that can
be studied
 require minimal investment to develop and administer
 relatively easy for making generalizations
 can also elicit information about attitudes that are
otherwise difficult to measure using observational
techniques
 but only provide estimates for the true population, not
exact measurements
 unsuitable where an understanding of the historical
context of phenomena is required.
 biases may occur due to lack of responses from
participants or because of the nature and accuracy of
the information received
 intentional misreporting to hide undesirable behavior
or confound the survey results
 respondents may have difficulty assessing their own
behaviour or poor recall of circumstance surrounding
their behaviour
 distinguish survey research from survey instrument
Qualitative Research designs
Phenomenological Design
• Examine human experiences through the descriptions
provided by the people involved.
• These experiences are called lived experiences.
• Aims to describe the meaning that experiences hold for
each subject
• used to study areas in which there is little knowledge
• The researcher must try to understand the situation
from the vantage point of the subject being studied
• The researcher must first identify what she or he expects
to discover and then deliberately put aside these ideas;
this process is called bracketing
• This will help the researcher to see the experience from
the eyes of the person who has lived the experience.
• Data analysis depends on the subjects description of
their lived experience
• the researcher then tries to attach meaning to the
subjects lived experience
• data collection and data analysis occurs simultaneously
Ethnographic studies
• involve the collection and analysis of data about
cultural groups
• “the systematic process of observing, detailing,
describing, documenting, and analyzing the life ways
or particular patterns of a culture (or subculture) in
order to grasp the life ways or patterns of the people in
their familiar environment”
• researcher frequently lives with the people and
becomes a part of their culture to explore their rituals
and customs
• studies might involve an entire cultural group or a sub
culture
• Ethnographers interview people who are most
knowledgeable about the culture who are called key
informants.
• Data are generally collected through participant
observation and interviews
• The same with phenomenological study researchers
employ bracketing during data collection and analysis
• Data collection and analysis occurs simultaneously
Grounded theory studies
• Are studies in which data are collected and analyzed
and then a theory is developed that is grounded in the
data
• uses both an inductive and a deductive approach to
theory development
• Employs purposive than probability sampling
• Data is collected in a naturalistic setting by employing
participant observation and interviews
• Data collection and analysis occurs simultaneously
• It involves a process of constant comparison where data
are constantly compared to data that have already been
gathered
• Pertinent concepts are identified and assigned codes.
• Once concepts have been identified and their relationships
specified, the
researcher consults the literature in search of any similar
associations
• This method is quite different from quantitative methods in
which the literature is always
consulted early in the research process
• Early consultation of literature may lead to premature closure
• the researcher may go into the research setting expecting to
find what is reported in the literature
• presumes the possibility of discovering fundamental patterns
in all social life.
• more concerned with the generation rather than the testing
of hypotheses
Historical studies
• Concern with the identification, location, evaluation, and
synthesis of data from the past.
• not only to discover the events of the past but to relate
these past happenings to the present and to the future
• It is like any other research where problems area is
identifies, research questions formulated, data collected
and analyzed
• Data is found in documents or in relics and artifacts
(primary & secondary sources).
• Primary sources may include : oral histories, written
records, diaries, eyewitnesses, pictorial sources, and
physical evidence
• The data for historical research should go through two
types of evaluation (Internal and external criticism)
• External criticism referrers to the authenticity or
genuineness of the data
• Internal criticism examines the accuracy of the data and
is considered after the data are considered to be
genuine
Action research
• is a research approach that is grounded in practical
action at the same time focused on generating,
informing and building theory
• is a type of qualitative research that seeks action to
improve practice
• studies the effects of the action that was taken
• Solutions are sought to practical problems by employing
actions that are to be tested in a specific context
• involves processes of collaboration, dialogue and action
among the participants
• starts with everyday experience and is concerned with
the development of living knowledge
Qualitative Vs quantitative research
 the two types differ in terms of the process a
researcher adopted to find answers to the research
questions
 The point of departure is the degree to which the
research study is analyzed by converting observations
in to numbers
 Differ also based on the type of questions asked, the
type of data (evidence) used and the method used to
process (analyze) the data
 quantitative research is a type of research that usually
applies the use of numbers to quantify the variation in
a phenomenon, situation, problem or issue.
 It emphasizes precise measurement based on
statistical and numerical analysis of data.
 It is much more organized in terms of the instruments
used and the questions asked compared to qualitative
research
 Data is available in the form of numbers.
 Data is gathered by using structured instruments.
 The researcher is objective giving less attention to
behavior, attitudes & motivation of its respondents.
 On the other hand qualitative research has more focus
on describing a situation, phenomenon, problem or
event than quantifying it.
 emphasizes on detailed verbal descriptions of how people
understand and explain their own world
 So it gives due attention to behavior, motivation & attitude
of people.
 It makes use of less structured instruments like in depth
interview, participant observation or an in depth analysis of
individual case
 Statistical procedures or in depth mathematical analysis is
not required for data analysis
 Findings are typically expressed by quoting interviews from
respondents or describing the researchers’ field experience
 It is more subjective since the researchers’ judgments
matters in data analysis
 The type of research question dictates the choice of
method
 Qualit. Res. is a systematic subjective approach used to
describe life experiences and give them meaning
• Quan. Res. a formal, objective, systematic process for
obtaining information about the world. A method used
to describe, test relationships, and examine cause and
effect relationships
 Qual. Rese. to gain insight; explore the depth, richness,
and complexity inherent in the phenomenon.
• Quan. Res. to test relationships, describe, examine
cause and effect relations
• qualitative research focuses on complex and broad
issues while quantitative research focuses on narrow
and concise issues
• Qual. res. is holistic while quantitative research is
reductionist
• Qual. res. follows inductive reasoning approach while quan.
res. follows deductive reasoning approach
• Qual. res. emphasizes on meaning & discovery while quan.
res. emphasizes on cause and effect relationships
• Developing vs testing theory
• Shared interpretation of ideas Vs control
• Communication and observation Vs structured instruments
• Basic elements of analysis: Words Vs numbers
• Individual interpretation vs statistical analysis
• Uniqueness vs generalizations
Sampling: meaning and process
What is sampling?
 Who should be contacted to gather empirical evidence
for the study?
 Not every member of the study population can be
contacted
 the researcher has to select some part of the study
population and conclude about the whole
 Sampling refers to he process of selecting a few (a
sample) from a bigger group (the sampling population) to
become the basis for estimating or predicting the
prevalence of … a situation regarding the bigger group.
 A sample is the sub group of the bigger group that the researcher
is interested in.
Why sampling?
1. Economical expenditure
2. Greater speed
3. Greater scope (for information)
4. Greater accuracy
5. Practicability
Disadvantage:
 Sampling may not enable to represent the whole characteristics
of the study population hence error.
 Error is unavoidable unless the whole population is considered
 Hence using appropriate sampling will help to minimize the
margin of error in measurement
 However, some level of error has to be tolerated
The sampling process
1. Defining the study population (the universe)
2. Specify the sampling frame (physical material from
which the sample is chosen)
3. Specify the sampling unit (depending on the nature of
the study the sampling unit may be one or more so
specify)
4. Specify the sampling method
5. Determine the sample size
6. Specify the sampling plan (operational procedure
regarding how each sampled unity will be
communicated )
7. Selecting the sample
 The most vital consideration in the choice of the sample is to
ascertain its representativeness
 That could be ensured by following accurate procedures and
use appropriate sampling technique
Techniques of sampling
 Broadly classified in to probability and non probability
sampling technique
A. Probability sampling technique
 Allows each element in the study population equal and in
dependent chance of being selected as a sample
 Every member of the study population has equal chance of
being represented in the sample avoiding the researcher's
preference
 Independence: The selection or rejection of a unit is not
influenced by the selection or rejection of another unit
Simple Random Sampling technique
 Each and every element in the total population has
equal and independent chance of being selected
 Each and every elements in the total population will be
allotted with specific number.
 Later on sample will be drawn in the form of lot until we
reach a determined sample size
 The selected numbers will be part of the sample from
whom data will be gathered
 Sample is selected without replacement (no additional
chance is offered once a unit is selected)
Stratified Random Sampling
 If the study population contains different groups with
homogeneous character this sampling technique will be
appropriate
Eg. If the study is about homeless people living on the
street containing children, middle and old age people,
men and women etc… the researcher has to
accommodate all these people
 After this stratification sample will be selected from
each non-overlapping groups using the simple random
sampling technique
 Sample could be determined proportionally or
disproportionally
Cluster Sampling
 Stratified sampling is employed for small number of
study population.
 employed when required to select sample from
large number of population scattered across large
geographical area
 first you select randomly natural groups/units
called clusters from the whole study population
(universe).
 the researcher first divides the study population in
to groups called clusters
 elements could be further selected from each
cluster based on simple random sampling
 What if you want to conduct nation wide survey
of institutional trust in Ethiopia
 first you go for 9 regional governments
 some regional governments may fall in the sample
 Zonal governments from each regions
 Woreda level administration
 Kebele & House holds and respondents
 In this example the population is already classified
by administrative units
 the researcher’s ability is critical to categorize the
population in to groups at each stage when this is
not the case.
Non Probability sampling
 applies when there is no way to estimate or
ascertain that each elements in the study
population has an equal & independent
chance of being included as a sample
 sample is selected based on the researchers
own preference & based on the criteria of
convenience.
 selection of sample in mainly based on other
considerations than random selection to
represent the whole study population
 employed when the number of elements in the
study population is unknown or cannot be identified
by the researcher for different reasons
e.g. number of visually impaired people in a woreda,
number of beggars in a kebele, number of street
children in a town etc….
Quota sampling
 respondents are selected non randomly according to
some fixed quota
 researcher specifies to communicate a certain group of
people with similar attributes and goes to the place
where he can obtain such people.
 samples are usually selected from a place where it is
convenient for the researcher to easily get the target
population
 total number of population may be known or unknown
 The two types of quota sampling (Proportional or non-
proportional)
• Proportional quota sampling different categories of
the study population are represented proportionally in
selecting sample.
• Your study population for instance could be street
vendors in Jimma Town
• Let we assume their total number is estimated to be
one thousand but scattered and unregistered
• you can disaggregate the data in to different categories
such as educational level, age, religion, race, gender etc…
• You can assign quota for each groups if the proportion of
each is already known
e.g. 600 female and 400 male
You can assign quota according to the same proportion
• Non proportional quota sampling the researcher
simply specifies the minimum number of sampled
units from each category with little concern for
numbers that much proportions in the population.

• In this case, either the proportion of each category


in the study population is un known or assigning
quota may not be necessary due to the nature of the
research
Accidental/ haphazard / convenience sampling
 is usually based on the convenience in accessing the
sampling population
 a researcher may go out on the street, pick any body and
collect data about a certain issue
 data collection may continue until the sample size reaches to
a certain predetermined level
 The sampling is accidental in that, respondents are identified
accidentally and based on their availability at some point in
time and place
 many of these respondents may not have information on the
issue
 Respondents may have little clue about the issue under study
e.g. opinion survey on solid waste management of a town
Purposive/ Judgmental sampling
 The main consideration in employing this technique
is who can provide with detailed information about the
issue under the study
 the researcher uses his own opinion to go to those
people who have rich information and are willing to
provide
 Personal experiences, exposure, responsibilities etc.. of
the respondents is the main consideration in in selecting
them as key informants
 More applicable when there is a need to identify a
typical case, to construct a historical reality, to describe
about an unfamiliar phenomenon
Snowball sampling
 sampling by recommendation
 more applicable when the potential respondents for
a study are hidden and difficult to access
e.g. prostitutes with HIV-AIDS
 The researcher tries to access at least one
respondent at the beginning
 the same respondent will be asked to indicate
others for data collection
 Such process will continue (recur) until the
researcher gets sufficient number of respondents
Chapter IV Methods of Data Collection and
Data Analysis
Data Collection Techniques
 The selection of methods for data collection depends up on
what kind of information is sought, from whom and under
what circumstances
Two major sources of data;
A. Primary sources
 First hand information or information from the original source
 It provides direct, unmediated information about the object of
study
 There are several methods but the choice of a method
depends upon; the purpose of the study, the resource available
and the skills of the researcher
B. Secondary sources
Methods of primary data collection
1. Observation
 Observation is a purposeful, systematic and selective
way of watching and listening to an interaction or
phenomenon as it takes place.
 Data collection in a natural setting as the actions and
phenomenon are taking place
Eg. If you wanted to study work performance, interaction
in a group, evaluate teaching-learning method etc…
 Participant observation
 Non-participant observation
Advantages
 Information is collected in a natural setting and avoids
artificiality in response
 Provides real life and real world information
Disadvantages
 If they know that they are being observed individuals or
groups may change their behavior (-ve or +ve)
 Observer bias
 Interpretation may differ from on individual to the other
 Incomplete observation (competing needs may arise
between recording in detail and watching keenly)
2. The interview
 Interview is an oral conversation with purpose where
the interviewer (one seeking the information) and the
interviewer (respondent) meet face to face to gather
information
 It helps to observe the real motives and emotional
condition of the respondent compared to a self
administered questionnaire
Types of interviews
 Unstructured interviews
 Structured interviews
 Semi structured interviews
2.1 Unstructured interviews
 the interviewer do not prepare a list of questions that
should be raised
 comes up with a general view of the issues to be raised
 At freedom to choose the wording and direction of the
discussion
Types of unstructured interview
A. In depth interview: frequent face to face meeting
between the researcher and the informant intended
towards understanding the latter's perspectives
B. Focus Group interviews: is an interview conducted
with a group
 Members of the group must have some experience in
common with regard to a situation or event
 broad discussion topics are developed beforehand
 Specific discussion points emerge as a part of the
discussion.
 Members of a focus group express their opinions while
discussing these issues.
C. Narratives
 much less unstructured than FGD’s
 have almost no predetermined contents except that
the researcher seeks to hear the personal experience
of a person with an incident or happening in his/her life
 The informant talks a lot and the researcher is passive
 Very effective to gather sensitive information
C. Oral histories
 More commonly used for learning about a historical
event or episode that took place in the past
 Involves passive and active listening
 Narratives are more about a person’s personal
experiences whereas, historical, social or cultural
events are the subjects of oral histories.

 Generally Data collection through unstructured


interviewing is extremely useful in situations where in-
depth information is needed or little is known about
the area.
In interviews we have to avoid such questions;
 Long questions
 Double barreled questions
 Questions involving jargon
 Leading question (are you using your time
efficiently in the work place)
 Biased question (do you think Jimma is a good
place to invest)
2.2 Structured interviews
 The researcher asks a predetermined set of questions,
using the same wording and order of questions as
specified in the interview schedule
 An interview schedule is a written list of questions, open-
ended or closed-ended, prepared for use by an
interviewer in a person-to-person interaction (tool)
Structured interview is advantageous in that;
 It provides uniform information, which assures the
comparability of data.
 It requires fewer interviewing skills than does
unstructured interviewing
 Much of the preparation takes place before the interview
The interview schedule may incorporate;
• What the interviewer says by way of introduction
• Introductions to particular questions, groups of
questions
• The questions (word for word)
• Prompts (and how they are to be used)
• Response codes
• Possible ‘skips’ in sequence (e.g. where a ‘yes’ answer is
followed by a particular question, a ‘no’ answer by a
‘skip’ to a different question)
• Closing comments
• Reminders to the interviewer about procedure
2.3 Semi-structured interview
 Interviewers have their list of topics and want to get
responses to them
 It uses open-ended questions, some suggested by the
researcher (“Tell me about…”) and some arise
naturally during the interview (“You said a moment
ago…can you tell me more?”).
 Used to collect qualitative data by allowing the
respondent to explain his opinion (point of view)
 The focus of the interview is decided by the
researcher based on what he would like to know
Advantages
 very good way to understand feeling and emotions
 Respondents can speak in detail about something
 It helps to clarify complex questions and issues
 What should be discussed or not decided before the
interview
Disadvantages
 Demands much skills from the interviewer
 Frequent probes may guide the respondent to give a
response expected by the researcher
 Time consuming
 Detailed qualitative data difficult to analyze
 The interview schedule for semi-structured interview
involves simple list of elements like;
 Introductory comments (probably a verbatim script)
 List of topics heading and possibly key questions to ask
under these headings
 Set of associated prompts
 Closing comments
Content of the interview
1. Questions
 Close ended: are questions with fixed alternative
limiting the respondent to choose from two or more
fixed alternatives
 Scale items ask for a response in the form of degree of
agreement or disagreement (e.g. strongly
agree/agree/neutral/disagree/strongly disagree).
 Open ended: questions that provide no restrictions on
the content or manner of the reply other than on the
subject area
 Give more freedom to the respondent, enable to get
detailed Information but difficult to analyze
2. Probes: are devise to get the interviewee to expand on
a response when you observed that she or he has more
to give
 It may use further questions like; ‘Anything more? Or
‘could you go over that again? ‘‘what is your own
personal view on this?’
 More tactics are; A period of silence; An enquiring
glance , ‘mmhmm…’, Repeating back all or part of what
the interviewee has just said.
3. Prompts: suggest to the interviewee the range or set of
possible answers that the interviewer expects
 when the need arises the list of possibilities may be
read out by the interviewer
The most commonly used sequences/steps to conduct
interview includes;
 Introduction: interviewer introduces him/herself,
explains purpose of the interview, assures of
confidentiality
 Warm up: easy, non-threatening questions at the
beginning
 Main body of the interview: Covering the main purpose
of the interview
 Cool off: Thank you and good bye
Advantages of interview
 most appropriate approach for studying complex and
sensitive areas
 useful for collecting in-depth information.
 It allows the interviewer to supplement information
 Allows to clarify confusions as it happens
 Can be applied for any population category (Children,
illiterate, old people, visually impaired etc… )
Disadvantages
 time-consuming and expensive
 Data quality depends up on the quality of interaction and
researchers skill
 Interviewer bias in framing questions and interpreting
responses
3. Focus Group Discussion
 A focus group discussion involves gathering people from
similar backgrounds or experiences together to discuss a
specific topic of interest.
 Encourages free discussion participants with other group
members unlike other methods
 It is a form of qualitative research where questions are asked
about their perceptions attitudes, beliefs, opinion or ideas.
 Focus groups share many common features with less
structured interviews,
 The aims of FGDs goes beyond collecting similar data from
many participants at once.
 A focus group is a group discussion on a particular topic
organized for research purposes.
 This discussion is guided, monitored and recorded by a
researcher as moderator and facilitator
 Focus groups are used for generating information on
collective views, and the meanings that lie behind those
views.
 They are also useful in generating a rich understanding of
participants' experiences and beliefs.
FGDs could be more appropriate to:
• conduct research relating to group norms, meanings and
processes
• to explore a topic or collect group language or narratives to be
used in later stages
• To clarify, extend, qualify or challenge data collected through
other methods
FGDs should be avoided when:
 If listening to participants' views generates expectations
for the outcome of the research that can not be fulfilled

 If participants are uneasy with each other, and will


therefore not discuss their feelings and opinions openly

 If the topic of interest to the researcher is not a topic the


participants can or wish to discuss

 If statistical data is required. Focus groups give depth and


insight, but cannot produce useful numerical results.
Forming the groups for FGDs
 The composition of a focus group needs great care to get
the best quality of discussion.
 Groups mainly constitute people of similar experience in
the topic under discussion
 Such as the mix of ages, sexes and social professional
statuses of the participants etc…
 Interaction is key to a successful focus group discussions
 We may constitute either a preexisting or stranger groups
both having their own pros and cons
 Group size is an important consideration in focus group
research.
 The optimum size for a focus group is six to eight
participants
 Small groups risk limited discussion occurring
 large groups can be chaotic, hard to manage for the
moderator and frustrating for participants who feel they
get insufficient opportunities to speak
Instrument for FGD
 interview schedule for focus groups is most often no
more than a loose schedule of topics to be discussed.
 In principle;
 Questions should move from general to more specific
questions
 Question order should be relative to importance of issues
in the research agenda.
 In reality the order of discussing issues may be guided
by the nature of the discussion itself
 Usually, less than a dozen of predetermined questions
are needed
 the researcher will also probe and expand on issues
according to the discussion.
 The researcher should assume a skilful moderator role
 He/she should facilitate group discussion, keeping it
focused without leading it.
 Prevent the discussion being dominated by one member
 allow differences of opinions to be discussed fairly
and, & encourage passive participants.
4. Questionnaire
 A questionnaire is a written list of questions, the answers
to which are recorded by respondents
 Respondents read the questions, interpret what is
expected and then write down the answers
 Hence it is important that questions are clear and easy to
understand, logically sequenced with good layout
A questionnaire can be administered as;
 The mailed questionnaire (low response rate)
 Collective administration: on a captive audience like
students in a class room or people in a meeting
 Public places: shopping center, health center, hospital,
school or pub
 There could also be a self administrated questionnaire or
through enumerator
Forms of questions
 Open ended: the possible responses aren’t given
Eg. Age, marital status
 Close ended: the possible answers are set out in the
questionnaire or schedule
Eg. How do you explain the quality of education at JU?
what factors affect the development of Jimma town?
Advantages and disadvantages of open ended questions;
 It helps to get wealth of information allows respondents
to freely reflect their views but difficult for analysis
 Even if it allows respondents to freely express
themselves information could be lost if a respondent is
not a good speaker
 helps to check researchers bias in setting response
categories but bias could occur in recording
Advantages and disadvantages of close ended questions;
 Ensures the information needed by the researcher
obtained with fixed category for response
 Easy for analysis
However,
 A respondent may tick a category without thinking
through the issue
 The answer provided may not truly reflect respondent’s
opinions but the researcher's opinion or analysis of issues
 Investigators bias in listing response categories of his
preference
 The information obtained may lack depth and variety
Considerations in setting questions;
1. Close ended questions are more preferred from open ended
questions
 Open ended questions are difficult for coding and analysis
2. Specific questions are better than general ones
 Why is Ethiopia poor? What factors contributed to
Ethiopia’s poverty?
3. No opinion questions are preferred to opinion questions
 What is your opinion about the new family law? How do
you compare the new family law with the old one?
4. Ordering of questions: better to put general questions first
and then specifics
5. Wording: avoid equivocal words that could be subject to
interpretation
Constructing a research instrument
 Construction of instrument is an important aspect of
conducting research
 The data obtained depends on the quality of
instruments and the questions set
 A researcher should endeavor to ensure the validity of
the instruments for data collection by making sure that
the questions fit to the objectives, research questions
and hypothesis of the research
Procedures to be addressed in setting the instruments;
1. Clearly define and list all the specific objectives,
research questions or hypotheses, if any, to be tested
2. For each objective, research question or hypothesis, list
all the associate questions that you want to answer
through your study
3. Take each research question identified in step II and list
the information required to answer it.
4. Formulate question(s) to obtain this information
Validity and reliability
 Validity refers to quality and can be applied to any
aspect of the research process
 With respect to measurement procedures it relates to
whether a research instrument is measuring what it set
out to measure
 Validity refers to the establishment of a logical link
between the objectives of a study and the questions
used in an instrument, and the use of statistical analysis
to demonstrate this link.
 The reliability of an instrument refers to its ability to
produce consistent measurement each time.
 When we administer an instrument under the same or
similar conditions to the same population and obtain
similar results, we say that the instrument is ‘reliable

Secondary sources of data


Data Analysis
The analysis of quantitative data
 Quantitative data are data which are in the form of
numbers (or measurements).
 It requires simple organization of the data to complex
statistical analysis
 The data has to be transformed in to numerical values
called codes so that it could be analyzed manually or
through a computer software program
 A researcher has to develop a code book, code the data
and verify the coded data
Before analyzing the data the researcher should specify;
• Which variables you are planning to analyze
• How they should be analyzed
• What cross-tabulations you need to work out
• Which variables you need to combine to construct your
major concepts or to develop indices
• Which variables are to be subjected to which statistical
procedures
 In the frame of analysis the type of analysis to be
undertaken (e.g. frequency distribution, cross tabulation)
and the statistical procedures applied should be specified.
Analyzing qualitative data
 Qualitative data do most of the time appear in the form
of words
 There may be information overload during data
collection but the danger arises during analysis
 There is no clear and accepted set of conventions for
qualitative analysis
 Qualitative data could be used to supplementing and
illustrating the quantitative data from experiment or
survey
 Qualitative analysis remains much closer to codified
commonsense than the complexities of statistical
analysis
Deficiencies and biases corresponding to qualitative
data analysis
• Data overload- limitation on the amount of data
that can be dealt with (too much to receive,
process and remember).
• First impressions- Early input may cause large
impression so that subsequent revision is resisted.
• Information availability-information which is
difficult to get may be suppressed
• Positive instances-There is a tendency to ignore
information conflicting with hypotheses already
held and to emphasize information that confirms
them.
• Internal consistency-There is a tendency to
discount the novel and unusual.
• Uneven reliability-The fact that some sources
are more reliable than others tends to be
ignored.
• Missing information-Something for which
information is incomplete tend to be devalued.

• Revision of hypotheses- There is a tendency


either to over or to under react to new
information
• Fictional base- The tendency to compare with a base
or average when no base data is available.

• Confidence in judgment- Excessive confidence is


rested in ones judgment once it is made.

• Co-occurrence- co-occurrence tends to be


interpreted as strong evidence for correlation.

• Inconsistency- Repeated evaluations of the some


data tend to differ.
General strategies for analysis
1. Basing the Analysis on Theoretical
Propositions

 Most studies are is based on a particular set of theoretical


propositions

 This strategy can be a powerful aid in guiding the


analysis, indicating where and on what, attention should be
focused.
2. Basing the Analysis on a Descriptive
Framework
 In exploratory and descriptive case studies you
may not start with a theoretical framework

 An alternative is to develop a case description.

 The researcher should look for a set of themes,


or areas, linked to the research questions

 The description should give adequate coverage


of the case
3. Explanation building
 appropriate for explanatory case studies

 The goal is to provide an explanation of what is


happening in the case

 For instance it may involve building an initial


proposition/statement and comparing evidences
with the assumption. Later on revising the
assumption and comparing it with additional
evidences

 Repeating such process as many times as it is needed


4. Chronologies
 Is a way of organizing data from a case study over
time
 Data is organized in sequential time perspective
 It may serve a good way to establish historical
relations

5. Time series analysis


 analysis of the patterning of data over time
 concerned about what changes occurred
 Whether change in treatment induced discontinuity in
events
6. Triangulations
 particularly valuable in the analysis of qualitative data
where the trustworthiness of the data is always a worry
 testing one source of information against other sources
 Both similarity and disparity are of value
 Giving the same message may mean cross validating
while discrepancy calls for further explanation
 Triangulation helps to validate information and improve
the quality of data
7. Key events
 used in ethnographic style case studies where they are
widely used to form a focus for analysis
Unit V- Format and style in Writing Research
5.1 Report writing in research
 the final step in research process, but still the most important
one
 Clear communication of what is done, why it is done and its
outcomes is very crucial
 After all the challenges to do the research readers get the
final and written copy of it
 the first impression on your research rests on the clarity with
which the report is presented
A research report refers to;
A well researched, clearly written, balanced, logical, objective,
impartial and concise document that presents conclusions
simply and clearly. It has a clear purpose, is organized
systematically and targets a specific audience.
 How the main body is divided and sub-divided, the
language and grammar used, the sequences with
which issues are presented matters in affecting the
quality of the report
Writing for research is different from writing for other
purposes;
1. Writing for research is controlled : in what to write,
the words used, the ideas expressed and above all the
ideas have to be valid and verifiable
2. Writing for research is rigorous: accurate, clear, free
from ambiguity and bias, logical and concise.
3. Written cautiously: defendable , should not assume the
knowledge of readers and avoid sophisticated jargons
The quality of a research report could be affected by;
 Skill in language and communication
 Ability to express ideas in logical and sequential manner
 previous knowledge in the area of the research &
 Research experience
Guiding points to improve the quality of a research report;
1. Plan before writing (Purpose, format, structure)
2. Use simple terminologies (to avoid barrier to commn.)
3. Clarity in language (orderly presentation, smoothness of
expression& economy of expression )
4. Use of mechanical aids for clarity of presentation
(Headings, sub headings, charts, graphs, tables etc…)
5. Avoid biasedness and emotionality
Basic components of a research paper;
1. The preliminaries
1.1 The title page
 Contains the title, name of the author and date
 The title should be brief, concise and show the central
idea of the research
1.2 Acknowledgment
1.3 Table of contents
1.4 List of tables, figures and appendices
1.5 The abstract
2. The Introduction
3. Results and discussions
 graphs, charts, tables etc…
 quotations, narrations, descriptions etc…
 The researcher should divide the report in to chapters,
sections and sub sections and decide which idea falls in
which category
 This part could be divided in to two parts as results and
discussions
 The result section simply summarizes the data collected
and it mentions all relevant results
 The discussion part deals about the implications of the
results of the data discussed in the previous part
 Conclusions will be drawn from the inferences in the
analysis part
Reference and bibliographical list
 The reference list provides all these referred
materials in alphabetical order
 No book which is cited or quoted in the report
should be missed in the reference list
 Bibliography consists of all books & other materials
which the researcher read in the course of doing the
research
Quotation, citation and plagiarism
 In writing your research report you may use others
work to support your arguments
 Problem identification, building theories for your study
and even framing your method requires referring
others work
 To do so either you directly quote others work in to
your report or paraphrase it and take only the idea
 In both case, the researchers needs to follow rules
 Quotation refers to taking others idea word by word
(verbatim) with out changing the content & wording
 On the other hand paraphrasing implies only taking the
idea and express it your own way
 The rules of citation applies in both cases to
acknowledge the original source of ideas
Two major rules apply when taking direct quotation;
 Merge with paragraph for quotations constituting 40
words or less (the statement inserted in to quotation
mark)
Eg:- Development cannot be measured by making use of a
single variable i.e. an increase in per capital income.
Miller (1999:120) stated that, “Development
encompasses multi dimensional faces. It has both
qualitative & quantitative aspects in changing the life
condition of people” Based on this we can argue that, an
increase in per capita income cannot be the only
measure of development.
 A quotation of more than 40 words has to be written in
a new paragraph and indented
Eg:-
Even if some people argue that growth in per capital
income can be a dominant measure of economic
development others still follow different line of
argument. For instance miller (1999:120) argued that;
Instead of simply calculating the ratio of GDP to the total
number of population we need to asses how much of the income
generated is fairly distributed among the population at large. We
need to analyze qualitative changes like how much the people is
educated, how much the poor is affected, how much equality is
attained… therefore per capita income could not be a good
measure of development.
Citation
 Is a way of recognizing the original source of idea to our
research
 For instance if you paraphrased the following idea from
an author called Daud Miller from a book published in
1999 and from page 120 you may cite it as follows;
The link between decentralization and development is still an
area that requires an in depth research & analysis. No body
denies that decentralization can effect people centered
development by making administration much more nearer to the
people. Moreover imposing every thing from the centre is now
becoming an old fashioned approach in line with the emergence
of the new dimension i.e. development from below (Miller,
1999).
Plagiarism
Consequences
 Lack of academic credibility and acceptance.
 Dismissal or suspension from an academic institution
in which one is learning or conducting research.
 Revocation of academic license.
 In the worst case legal punishment after taking cases
to court.
Formats of referencing
 Reference list consists of all the materials that were cited and
quoted in the main body of your research report on the other
hand bibliography ….
 References cited or quoted in the text must also appear under
the reference list in alphabetical order having identical year and
name in both sections
A complete reference data should consist of;
 the name of the author, year of publication, the title of the book
(research) , volume number (if any), edition number (if any), place
of publication, publisher and any other information necessary.
 There are varieties of formats of referencing but you need to
adopt and consistently apply the same across your report eg.
Chicago, APA (American Psychological Association), CSE (Council of
Science Editors), MLA (Modern Language Association), Turabian
 We adopted APA for our course and department
Unit 6
Ethics in Research
Ethical consideration in research
 Ethics is a key issue in research in defining the expected
ethical behavior of the major stakeholders in research
The major stakeholders in research include;
 The participants or subjects
 The researcher
 The funding body
Ethical issues related to the participants;
A. Informed consent
 Informants should be properly informed about the
type of information needed, why it is needed, for what
purpose it , how they are expected to participate , and
affect them.
 Consent should be voluntary and without pressure
 Informants should be competent enough to give
consent, well informed for reasoned consent and
unforced
B. Confidentiality and anonymity
 Sharing the information about the informant for
reasons other than the research is unethical
 The information should be kept anonymous
 The researcher has to make sure that the source of the
information is unknown once it is collected
C. The possibility of causing harm to respondents
 What possible harm could the research cause on
respondents
 health hazard, discomfort, anxiety, harassment, invasion
of privacy or demeaning or dehumanizing procedures.
 The researcher needs to examine carefully whether their
involvement is likely to harm them in any way
 Should minimize the risk to the least minimum possible
level
 The harm should not be greater than ordinarily
encountered in daily life
D. Seeking sensitive information
 Certain type of information can be regarded as sensitive or
confidential and hence invading respondents’ privacy
Eg. Drug, rape, sexual behavior, even age, income etc..
 However, the researcher can’t afford to skip the questions
or the research will not proceed
 the researcher should be careful about the sensitivities of
your respondents
E. Deception
 Avoid intentional deception of the participants over the
purpose and general nature of the investigation
 The researcher should plainly explain to respondents right
to withdraw from the research at any time and their
recording be destroyed
Ethical issues relating to the researcher
A. Avoid bias
 Bias is a deliberate attempt either to hide what you
have found in your study, or to highlight something
disproportionately to its true existence
B. Use appropriate research methodology
 Unethical to use inappropriate research method
Eg. Selecting a highly biased sample, using an invalid
instrument or drawing wrong conclusions
C. Providing incentives
 respondents should consent after understanding the
importance of the research than to get money
 However a small gift after collecting the information as
a gesture of appreciation might be alright
D. Incorrect reporting
 To distort the information and report it in a way that
favors the researcher’s or others interest is unethical
E. Inappropriate use of the information
 in a way that damages the informants, the study
population or any other target is unethical
Ethical issues from the sponsoring organizations
A. Restrictions
 On the methods used, on reporting the exact findings,
from publishing the study, methodology used etc… is
unethical
B. Misuse of information
 To wrong management agenda, to silence employees or
customers etc…

You might also like