This chapter contains definitions, procedures, and explanations of techniques used to collect, analyze and present information. The section deals with the description of the methods applied in carrying out the study.


Research design is the conceptual structure within which research should be conducted. Research design provides the glue that holds all the elements of a research study together. It indicates how all of the major parts of the research project work together to try to address the central research questions. It is the scheme, outline or plan that is used to generate answers to research questions. It is an arrangement of conditions for collection and analysis of data. The function of research design is to provide for the collection of relevant information. It constitutes the blue print for the collection, measurement and analysis of data.

Selection of Research Design:

In selecting a research design one should consider the following:

  • What the study is about- Objectives of the research study.
  • Why the study is being carried out
  • Where the study will be carried out
  • Method/techniques of Data Collection to be adopted
  • Time required
  • Data Analysis– qualitative and quantitative

In selecting a research design a researcher should :

  • Name and describe the research design
  • Justify why it was selected
  • Explain how it will be used.
  • One must state the rational for selecting the research design


  1. a) Descriptive Research Designs

This design describes phenomena as they exist. Descriptive studies generally take raw data and summarize it in a useable form. Descriptive Research addresses issues of who, what, where, how related to research. It provides further insight into the research problem by describing the variables of interest.  This method can be used for profiling, defining, segmentation, estimating, predicting, and examining associative relationships. In a descriptive study, no attempt is made to change behavior or conditions. One measures things as they are.  This method describes the state of affairs as they are. It results in the formulation of knowledge and solutions to problems. The focus of interest is the respondent’s opinion and views. Questionnaires/interviews are mainly used to gather information.

  1. Experimental Research Design

This design is used to test the cause-effect relationship through the manipulation of variables. The experimental group is manipulated while the control group is not. Environmental factors are also controlled. It involves the systematic manipulation of some characteristics and examination of the outcome. In an experimental study one take measurements, try some sort of intervention, then take measurements again to see what happened.

  1. Correlational Research Design

This method determines whether or not and to what extent an association exists between two or more variables. Data is collected from varied groups of subjects and then compared for their similarities and differences. It provides procedures for understanding relationships. It enables the researcher to assess the degree of relations that exist between two or more variables.

  1. Case study

This is an intensive, in-depth analysis of a single entity. It aims at gaining in-depth insight of an issue using smaller samples. The findings can be generalized to a wider population. It seeks to describe a unit in details. In a case study a great deal can be learned from a few examples of a phenomenon under study. It is an in-depth study of an individual group, institution, organization or program. Data gathering include interviews, field notes of observations, archival data and biographical data.

  1. Survey Design

This is an investigation of views from   a wider population such as the opinion polls. These are general views affecting a wider group in general. The method is used to analyze and discover occurrences. It explains events as they are, were or will be.

  1. Exploratory Research

Designed to generate basic knowledge, clarify relevant issues uncover variables associated with a problem, uncover information needs, and/or define alternatives for addressing research objectives. This is a very flexible, open-ended process.

  1. Historical research

This refers to exploration, explanation and understanding of past phenomenon from data already available. It is the Collection and evaluation of data related to past events that are used to describe causes, effects and trends that may explain present or future events. Data are often archival. It aims at arriving at conclusions about causes, trends, and effects of past phenomenon in order to explain the present and predict and control the future. This method is useful where primary data cannot be collected.

  1. Cross cultural research design

This method is mainly used to analyze to what extent cultural beliefs and practices in ones immediate environment influences ones attitude hence development.

A sample is a subset, a portion or a segment of a population that is used to represent the entire group as a whole. It is a specimen representative of a group and comprises a set of elements drawn from and analyzed to estimate the characteristics of a population. When doing research, it is often impractical to survey every member of a particular population because the total number of people is simply too large. It is therefore more sensible to draw conclusions of an investigation from observing a sample representative of the whole population.


A Sample is a representative group of the population on which the research data is to be              obtained. Sampling is the process of selecting some parts of an aggregate or totality on the basis of which judgment or interference is made. According to Parkash (1985) a sample is a finite part of a statistical population whose properties are identified for research .Sampling involves selecting a number of individuals to participate in research study. The basic idea of sampling is that by selecting some of the elements in a population, we may draw conclusions about the entire population.

A census is a count of all the elements in a population. A census is feasible when the population is small and necessary when the elements are quite different from each other. When the population is small and variable, a census is applied. .

Advantages of Sampling

  • It is cheaper to administer when compared to a census.
  • It saves on time and cost
  • It has the possibility of better testing and more thorough investigation
  • It provides results faster than a census.
  • In some cases, it would be dangerous to use an entire population e.g. when testing vaccines or medication
  • Most appropriate in some experiments where destruction is involved

Steps in Sampling Procedures

  • Define the population. This is determined by the purpose of the study.
  • Determine the sampling frame. This is a list of objects from which the sample will be drawn. Sampling frames can be obtained from research agencies, government departments and organizations.
  • Determine the sampling procedure i.e. probability or non-probability techniques.
  • The researcher must then determine the appropriate sample size. The larger the sample the more accurate the conclusions drawn are likely to be.
  • Finally the researcher then selects the specific study objects to be included in the sample.



Types of Sampling Designs

There are 2 types of sampling techniques; Probability & Non-Probability Sampling.


Probability sampling method is any method of sampling that utilizes some form of random selection. Verdugo (1998) explains that probability sampling is also known as random sampling or chance sampling. Under this sampling design, every item of the universe has an equal chance of inclusion in a sample. In this case, a lottery method is applicable in which individual units are picked up from the whole group not deliberately but by some mechanical process. It is by a blind chance alone that determines whether one item or the other is selected.


  • Ideal for statistical purposes


  • It is difficult to achieve a representative sample in practice
  • It requires an accurate list of the whole population
  • It may prove expensive to conduct as those sampled may be scattered over a wide area


Types of probability sampling

a)Simple Random Sampling

In this case, each member of the population has an equal chance of being chosen. The method is used when the group is homogeneous. There are several ways of achieving a random sample. Simple random sampling is simple to accomplish and is easy to explain to others. This includes the lottery method when names or numbers are written on pieces of paper and the lucky number is selected.

b)      Systematic random sampling

The researcher calculates a sampling interval, and the interval becomes his or her own quasi random selection method. The starting number is an integer that must be less than the total number of individuals in the population. This integer will correspond to the first subject. The interval will serve as the constant difference between any two consecutive numbers in the progression.

c)Stratified random sampling

This method involves the division of a population into smaller groups known as strata. It is used when the group is heterogeneous with the aim of ensuring that all categories participate in the study. The researcher looks at the variables that are likely to affect the results, and stratifies the population in such a way that each stratum becomes a homogeneous group within itself. Then draw the required sample by using the table of random numbers. A stratum is a subset of the population that share at least one common characteristic.


  • Stratification will always achieve greater precision provided that the strata have been chosen so that members of the same stratum are as similar as possible in respect of the characteristic of interest.
  • It is often administratively convenient to stratify a sample as the results from each stratum may be of intrinsic interest and can be analyzed separately.
  • It ensures better coverage of the population than simple random sampling.


  • Difficulty in identifying appropriate strata.
  • More complex to organize and analyze results.

d) Cluster Random Sampling

This is a survey method in which groups i.e. clusters of sampling units but not individual units, are selected from a population for analysis. The purpose of cluster sampling is to sample economically while retaining the characteristics of a probability sample. Groups or chunks of elements that, ideally, would have heterogeneity among the members within each group are chosen for study in cluster sampling. This is in contrast to choosing some elements from the population as in the other methods described above.


  • saving of travelling time, and consequent reduction in cost
  • useful for surveying employees in a particular industry, where individual companies can form the clusters


  • units close to each other may be very similar and so less likely to represent the whole population
  • larger sampling error




In non-probability sampling, the sample is not based on chance. It is determined by a person. It is not possible to assign to an element of population the probability of its being selected in the sample. One may use his/her personal judgment in the selection of the sample. In this case the sampling is called judgment sampling. This sampling does not use random selection. Respondents are selected at researcher’s discretion. These are individuals that the researcher feels will offer vital information. This method involves the following:

  • Purposive/judgmental sampling
  • Accidental/haphazard /convenience sampling
  • Quota sampling
  • Snowball sampling


1. Judgmental/purposive sampling  

In this form of sampling the researcher targets respondents that may provide the information being sought for. There is a specific predefined group that the researcher is seeking. The selection of respondents is based on whether they fit in the researcher’s judgment of an appropriate group. The researcher relies on his/her expertise to select respondents that the researcher thinks are representative of the target population.

2. Accidental/Haphazard /convenience sampling

This is the use of clients who are available at the time of study for example, the media interviewing someone on the street to get a quick response on an issue. The researcher simply selects a number of respondents who are conveniently available when the researcher is around. This method is simple to use as it saves time and cost. However it is difficult to determine to whom the results apply.

3. Quota Sampling

Respondents are selected according to a fixed quota. Parkash (2007) explains that, Quota sampling involves dividing the population into sub-groups based on variables known about them and then purposively selecting samples from each sub-group or strata.

4. Snowball Sampling

In this method a researcher identifies a respondent who meets the criteria for inclusion in the study. The respondent identifies others. This method is useful when a researcher is trying to reach an inaccessible or hard to find respondents.

Difference between probability and non- probability sampling

i) Probability sampling Involves Random selection, non- probability sampling does not involve random selection.

ii) Probability samples can depend upon the rationale of probability theory, non-probability cannot.

iii) Probability Sampling represents the population well, non- probability samples, may or may not represent the population well.

v)The opposite of probability sampling is non-probability sampling, and simply means sampling without using random selection methods.






  1. Types of research instruments.

There are three major types of research instruments. These are

  • Questionnaires
  • Interviews
  • Observation


These are research instruments that gather data over a large sample. Respondents note down their views. Each person is asked to respond to similar questions.

Advantage Disadvantage
Information can be collected from a large sample and in diverse regions. Response rate can be quite low.
Confidentiality is upheld. No direct contact so researcher cannot deal with any misunderstanding or clarify. There is no opportunity to ask for further information related to answers given
Saves on time -economical to use .Needs respondents who are literate
Since they are presented on paper format there is no opportunity for interviewer bias. No clear reason can be given for incomplete responses.
Easy to analyze\administer May omit important information required in study.

Types of questionnaires

  1. Self administered questionnaires
  2. Postal\mail questionnaires.

Self administered questionnaires

This refers to cases where the researcher hand delivers the research instrument

Advantage Disadvantage
Response rate is high. Costly
Researcher interacts with respondents. Issues can be clarified Time consuming
Researcher can observe situation. Cannot reach large numbers- limited scope.


Post/mailed questionnaires

This refers to questionnaires that are sent to respondents through the mail.

Advantage Disadvantage
Cost of collecting data in terms of time and finance is low. Response rates can be quite low
Confidentiality is upheld. No direct contact so researcher cannot deal with any misunderstanding or clarify
Since there is no face to face interaction bias is reduced. There is no opportunity to ask for further information related to answers given.
Large numbers of respondents can be reached. Requires respondents with postal services
Ideal when subjects are dispersed geographically apart. No way of knowing if intended respondent actually completed the questionnaire



Refers to oral administration of questions

Advantage Disadvantage
Provides in depth information Expensive- the researcher has to meet respondents
Questionnaires can be clarified Requires high skill in communication
Flexible; Interviewer can adapt to the situation Interviewers bias and subjectivity can occur
Sensitive and personal information can be extracted Requires a small sample.
Probing questions can be used Respondents can react to interviewer, may become bias
Higher response rate  


Types of interviews


Structured/ unstructured interviews

Structured interviews

Advantage Disadvantage
Systematic/organized Rigid therefore in-depth information not gathered
Easy to analyze Can be biased
Saves on time  

Unstructured interviews

Advantage Disadvantage
Minimal control over the sequence of answers. In-depth information can be gathered Difficult to analyze data
Sensitive topics can be studied Time consuming
Respondents are relaxed not intimidating irrelevancies



This refers to cases where the researcher has direct communication (face to face) with respondents.

Advantage Disadvantage
Response rate is high Costly
Researcher interacts with respondents. Issues can be clarified. Time consuming
Researcher can observe situation and witness non verbal behavior Cannot reach large numbers- Limited scope.  Geographical limitations.
Researcher can pick up any non-verbal cues. Respondents may be uncomfortable.


This refers to oral questions asked through the telephone.

Advantage Disadvantage
Cost of collecting data in terms of time and finance is low. At times cheaper to call than travel. Can be very expensive
Confidentiality is upheld. Respondents may be more relaxed and respond better. Respondents may not be honest
Since there is no face to face interaction bias is reduced. Respondents may be impatient. This may affect accuracy of results. Respondents can terminate concentration.
Large numbers of respondents can be reached. Researchers may not establish trust.
Ideal when subjects are dispersed geographically apart. Respondents may refuse to participate or answer some questions.
Easy accessibility and speed. Allows research to make contact with respondents with whom it may have been impossible. E.g. outside countries Not able to get non-verbal communication.
Eliminates any discomfort that may have occurred face to face.  



There are group interviews where the researcher acts as a facilitator.

Advantages Disadvantages
Detailed information can be got. Some respondents may dominate conversations thus affecting its reliability.
Because of several respondents a variety of ideas can be suggested. Time consuming.
Reliable information may not be collected. Results may be unreliable.
  Difficult to analyze results.



This is a research instrument that deals with analyzing what people do. It involves the systematic watching, recording, analyzing and interpreting of people’s behavior.

Advantage Disadvantage
Detailed information can be got Not all behaviors can be observed
Researcher shares experience of respondents Limited number of respondents can be studied
Reliable information may be collected. Results may be unreliable
  In studies where more than one observer is needed training should be undertaken.

Types of observations:

  1. participant observation
  2. non-participant observation

Participant observation

This refers to a study I which the observer becomes a part of or an active participant in the study. The subjects may not be told about the participant observer. The researcher attempts to participate fully in the lives and activities of the subjects. E.g. Phenomenological studies. Respondent becomes comfortable with researcher.

Advantage Disadvantages
Get detailed information Ethical can pose difficult ethical dilemma for the researcher.
Valid results Bias
Provides complete picture of the environment being studied. Difficult to quantify and interpret records.
Researcher shares experience. Impossible to accurately observe and write down everything. A lot of information may be left out. Data recording difficult for researcher.
All data collected useful Conflicts or emotional involvement may occur.
  Time consuming.

Non-participant observation

In this study, the participant is not directly involved in the situation to be observed. The researcher may not intentionally interact with respondents.

Advantage Disadvantage
Saves on time Observer may lack detailed information on the situation.
Confidentiality is upheld Researcher may not experience real situation.
Since there is no face to face interaction bias is reduced There is no opportunity to ask for further information related to the situation.
Easy to record data  



(Visited 142 times, 1 visits today)
Share this:

Written by