1. Problem identification
  2. Problem conceptualization
  3. Problem statement and justification
  4. Literature review and theoretical perspectives
  5. Objectives of a research
  6. Study designs

Problem identification

Researcher should research problems since there are a lot of problems that can be identified and studied.

It should be a specific problem in which you have knowledge about

It involves the existing theories, literature, discussions with experts, personal experience etc.

Therefore one has to start by identifying a broad area that she/he is interested in.

The area should be related to professional interest and goals of research e.g. education, low cost of living, problems of slums, poverty, HIV/AIDS scourge etc.

The researcher should then narrow down the broad area to specific problems; in selecting a specific problem a researcher should consider the key actors that help in researching the problem.

  1. The research should be an important one thus leading to findings that have widespread implications in that particular area.
  2. Challenge some commonly state of believing in reality
  3. View the inadequacies of the living laws/policies
  4. Cover a reasonable scope i.e. neither too narrow nor too general

Factors determining the Scope of research

  • Time
  • Money available
  • Availability of subject/object
  • Equipment available

Problem conceptualization/understanding

It involves knowing the problem one undertakes during research

It should be a specific problem in which you have knowledge about; it involves the existing theory, existing literature, discussion with professionals, previous research study through the media, personal experiences, replication etc.

Problem statement and justification

A research study usually starts with a brief introduction; the researcher briefly introduces his/her area of interest then the general area of study, then he/she narrows down to a specific problem to be studied.

This explains why you are investigating a particular issue; gives reason why you want to carry out research on that particular problem.

Characteristics of a good problem statement

  1. Write it clearly to capture the reads
  2. Let it be objective as possible to make it researchable
  3. Indicate the scope of the research problem
  4. State the importance/relevance the new knowledge would bring.

N/B: these characteristics are very important in justifying the problem stated; in stating the purpose, the researcher conveys the focus of the research study in one or two sentences. The purpose must be indicated clearly, must not be ambiguous, should indicate the concept of the study, the targeted population etc. e.g. 1. The purpose of this study is to investigate the income generating activities and how it affects women in small scale business in Kisumu. 2. The purpose of this study is to find out the relationship between income and poverty in the slums of Nairobi.

Literature review

It involves the systematic location, identification and analysis of documents containing information related to the research problem being investigated.

It should be extensive because it is aimed at obtaining detailed knowledge.

Its purpose is to learn about research already carried out in one or more aspects of research problems.

Purpose of literature/objectives

  1. To summarize the results of the previous research so as to form a foundation on which to form you own research.
  2. To collect ideas on which to call you own research.
  3. To collect ideas on how to gather data.
  4. To investigate methods of data analysis
  5. To study instrumentation
  6. To accept the success of various design of the study already undertaken.

Theoretical perspectives

It involves all the theories which probable and applicable on the research; this helps in the analysis and verification on the mode of research.

Objective of the research

It entails the aims of research

Here, the researcher clearly states the comprehensive aims and goals of his research.

The purpose of the study may be “to find out the relationship between income and expenditure within the slums in Nairobi.”

Formulating Hypothesis

Hypothesis is a researcher’s prediction regarding the outcome of the study; it states possible differences, relationships or causes between two variable and concepts.

In formulating hypothesis, the following can be used:-

  • Existing theories
  • Previous research
  • Personal observation
  • Experiences
  • Common sense

Purposes of Hypothesis

  1. They provide direction; they bridge the gap between the problem and the evidence needed for its solution.
  2. They ensure collection of the evidence necessary to answer the question posed in the statement of the problem.
  3. Enable the investigator to access the information he/she has collected from the stand point of both events and organizations.
  4. Sensitize the investigator to certain aspects of the situation that are relevant regarding the problem at hand. Researchers should however guard against being led to acceptance of false data or sensitization.
  5. It permits the researcher to understand the problem with greater clarity and use the data collected to find solutions to the problems.
  6. It guides the collection of data and provides the structure for their meaningful interpretation in relation to the problem under investigation.
  7. It forms the frame work for the ultimate conclusions as solutions; researchers usually base their conclusions on the results of the test of their hypotheses.

Characteristics of a good Hypotheses

  1. They must state clearly and briefly the expected relationship between variables.
  2. They must be consistent with common sense or generally accepted truths.
  3. They must be based on a sound ration derived from theory or previous research or professional experience.
  4. They must be testable; data can be collected to support or fail to support hypothesis. This also implies that the variables stated in the hypothesis can be operationalized.
  5. They must be related to empirical phenomenon; words like “ought, should, bad” reflect moral judgement and should be avoided.
  6. They should be testable within a reasonable time; for example, the hypothesis that children who are breastfed for longer periods have a longer life expectancy in adulthood would take more than 50 years to test.
  7. Variables tested in hypotheses must be consistent as the purpose statement, objectives and the operationalized variables in the method sections.
  8. A good hypothesis must be simple and as concise as the complexity of the concepts involved allows.
  9. It must be stated in such away that its indications can be deduced in the form of empirical operations with respect to which relationship can be validated or refuted.

The following are examples of hypothesis that meet the above criteria

  1. High alcohol content in the blood influences the reaction time among drivers in Kenya.
  2. High mathematics anxiety influences students’ performance in statistics questions at Kenyatta University.
  3. There is positive relationship between level of education and income among civil servants in Kenya.
  4. The amount of rainfall and type of fertilizer used influences the yield of wheat per acre in the Rift valley province in Kenya.
  5. The promotion as part of incentive programme increases productivity of workers in both public and private sectors.

N/B: Hypothesis can be expressed in a manner that seems to deny the variables of the parameters of study. This expression is usually given in a negative form (-ve). Such kind of hypothesis is called null hypothesis e.g. there is no difference in the performance o national examinations between standard eight from rural primary schools and standard eight pupils from urban primary schools in Kenya.

If the above null hypothesis was to omit the ‘no’ it would draw a relationship between variables.

A hypothesis that states that there is a relationship or a difference between variables is called an alternative hypothesis.

Research or study Design

Study designs

Once the objectives of the research project have been established; the issue of how these objectives can be met leads to a consideration of which research designs will be good.

Types of study design

  1. Cross design; it involves the collection of data on more than one case.
  2. Longitudinal design; it consists of repeated cross – sectional to ascertain how time influences the results.
  3. Experimental design; it differs from the 2 designs due to its greater control over the objective of its study. The researcher strives to isolate and control every relevant which determines conditions, the events investigated so as to observe the effects when the conditions are manipulated e.g. chemical experiment in the laboratory.

Sampling and sampling procedure

A sample is a group of people or object selected from a larger group.

It therefore refers to the process of selecting of people or objects from a larger group.

Sampling procedure

Steps which are well outlined and followed when doing research

Types of sampling

Probability/random sampling

Non probability/non random sampling

Probability/Random sampling

Each subject, person, group or object has an equal chance of being selected or picked.

If homogenous or heterogeneous then we use certain methods i.e. general pattern.

Non probability/non random sampling

It is based on selection by no random means.

This can be useful for certain studies but it provides on a weak basis for generalization e.g. snowball sampling

Methods of probability/random sampling

Simple random sampling

Systematic sampling

Simple stratified sampling

Cluster sampling

Multi-stage sampling

Simple random sampling

It is used when the population is uniform or has common characteristics in all cases e.g. medical students, community development students etc.

A simple form of random selection would be to pick names for sampling from larger population e.g. homogenous

Systematic sampling

Is an alternative random sampling and can be used when population is very large.


Cars, a particular model are being produced in a factory. It involves selection of units in series according to a predetermined system.

There are many possible systems; the simplest perhaps exist 9th in that case of a list e.g. every 10th person in a telephone directory or every a 100th model of the production line.

Simple stratified sampling

It should be used when cases in the population falls distinctively in different categories or strated e.g. business whose workforce is divided into 3 categories of production, research and management.

To achieve simple randomized sampling, an equally randomized sample is obtained from each strategy separately to ensure that each is equally represented.

Cluster sampling

It is used in cases when the population forms clusters by chairing one or some characteristics but otherwise as heterogeneous as possible e.g. travellers using main railway station. They are all train travellers with each cluster experiencing a distinct station but individual varies as to age, sex, and nationality.

It is also called Arc sampling; it is used when the population is large and spread over a large area e.g. representing different categories of the people.

Multistage cluster sampling

It is an extension of cluster i.e. clusters of successively similar size are selected from within each system e.g. random sampling of all UK universities then a random sample of modules being taught in those universities then a random sampling of the students doing a module.

Methods of random sampling

Accidental sampling (convenience sampling)

Involves what is immediately available, studying the building you happen to be in.

Researching on subjects or students in you own class.

The people cannot be checked or looked at if it’s the representative of all population.

Quota sampling (quantity)

Usually used by reporters interviewing in the streets

Attempts to balance the sample by selecting e.g. equal numbers of the case of study

Systematic marching

Used when 2 groups of any different sizes are compared by selecting a number from a larger to match the number and characteristics of a smaller one.

Non random sampling technique

Snowball sampling

It is where the researcher contact a small group or number of members of targeted people/woo people and get to introduce him/her to others e.g. prostitutes, drug addicts and then uses it to establish contacts with others.


Primary Data

Entails going out and collecting by observing, recording and measuring the activities and ideas of real people or perhaps watching animals or inspecting objects and experiencing events i.e. survey, research. Usually it is the 1st hand information through tape recording, interviewing, participant observation.

Secondary Data

It involves getting information on a ready work i.e. historical study, nation wide study, and official statistics.

It uses books, library services, archives, internet, journal, newspapers, galleries and government departments.

Simple observation

It is a method of recording conditions, events and activities through looking rather than asking. As an activist as opposed to a method, observation is required in research e.g. observing the result of experiment, the behaviour of models.

This refers to complete observation the observer takes a detached standards by not getting on an event of obtrusive observation techniques and remain invisible either in fact or in effect.

Participant observation

It involves the researcher engaging fully in life and the activities of the observation despondence also are aware of his/her observing role.

Complete participation observation

Here the researcher takes a full part in the social events but is not reorganized as an observer by the observed.

It is a cover observation (see and record in mind)

The research may live with the people/observed but remains anonymous.


This refers to a set of quizzes to be asked in an interview doing the research so as to collect the information.

There are 2 formats of administering the questionnaires i.e. closed ended format and open ended format.

Closed ended format

Is where despondence must choose from a choice of given quizzes e.g. what is your marital status?

  1. Single
  2. Married
  3. Widower

What is your religion?

  1. Christian
  2. Muslim etc.

Open ended format

Is where the respondence is free to answer in their own words; it opens up your personal opinions. They are not suitable for questions which require probing to obtain adequate information e.g. which characters do you look for in a spouse?

Do you think that the grand coalition government will be united till the end of the term?


These are face to face quizzes which are asked from the respondence; normally the quizzes to be asked are written down in a list provided so as to guide the interviewing process.

It is usually suitable when the researcher requires a more detailed and comprehensive or elaborate information e.g. on historical background/biography or job interviews. There are 3 forms of interviews:-

  1. Structured interviews
  2. Unstructured interviews
  3. Semi structured interviews


Structured interviews

These are standardized quizzes which are read out and may be closed.

Unstructured interviews

Usually based on in quiz format i.e. open ended

Semi structured interviews

Contain both structured and non structured factors and is usually open ended. It contains both standardized and non standardized features.

Data analysis methods

Data is the information obtained from the field



Frequencies etc.

Classification of data for analysis

Once the questionnaire or any other measuring instrument have been administered, the mass of raw data collected must be systematically organized in a manner that facilitates analysis.

If empirical or quantitative analysis is anticipated the responses in the questionnaire will have to be assigned in numerical values e.g. if the responses anticipated are yes or no, one will have to assign the no or one will assign yes and vice versa.

  1. Frequencies

These are scores in a specific variable; it gives a record of the number of times a score or a response e.g. in an educational research, frequency distribution will report the number of students who scored 30, 33, 34, 35, or 36 points on a test.

N/B: the total number of frequencies should always be equal to the number of sample size “n”, if this is not the case one should check the data for errors.

Bar graphs

Showa the distribution of nominal and domino variables; the categories of the variables are along the horizontal axis i.e. x-axis and the values are on the vertical axis (y). The basis should not touch each other.


Is a bar graph with the bars touching each other to produce a shape that reflects the distribution of the variables.


Shows values of variables as a section of the total cases e.g. slices of a pie

Research as defined by different people (scholars)

The Encyclopedia Oxford English Dictionary defines research as the systematic investigation into the study of materials, sources etc. in order to establish facts of each new conclusion.

It is an Endeavour, real facts by scientific study of a subject of critical or a course investigation.

Leady (1989) defined research as a procedure by which we attempt to find systematically and with the support of the demonstratable facts, the answers to quizzes or solutions to the problems.

Ker linger (1970) defined research as the systematic/control empirical and critical investigations of hypothetical propositions about presumed relations among natural phenomenon.

Mouly defined research as a process of arriving at effective solutions to a problem through systematic collection analysis or interpretation of data.

Social Research

Social science research is a “catch all” term that includes research in any facet of life in society.

Social research focuses on social interrelationships, social opinions, customs, habits, communities etc.

It thus involves carrying out a diligent inquire (systematic control, empirical) or certifiable examination of human behaviour, its causes and consequences.

Social researchers thus try to look at factors within society and also try to find ways to understand and explain human actions and results of these actions.

Social science research is relevant to a wide range of discipline i.e. a part from sociology, researchers can be specialists in subjects such as education, health care etc.

(Visited 147 times, 1 visits today)
Share this:

Written by