OBJECTIVES & COURSE OUTLINE

BROAD OBJECTIVE

•By the end of these sessions, the students will be able to acquire knowledge and skills in developing a research proposal as well as conducting a research project

SPECIFIC OBJECTIVES

By the end of the sessions, the students will be able to:

•Explore the basic concepts of research

•Explain the role of research to clinical practice

•Describe the major research types

•Describe the research process

•Develop & implement a research proposal

SCIENTIFIC DEFINITION OF RESEARCH

•According to Burns and Grove (1999: 3), the word ‘research’ means ‘to search again’ or ‘to examine carefully’.

•Research is diligent, systematic inquiry or study to validate and refine existing knowledge and develop new knowledge.

•It is a scientific and systematic search for pertinent information on a specific topic.Research is a form of systematic enquiry. This means literally that research is carried out with regard to a predetermined system, or research methodology, which is theoretically informed

Nursing research cont’

•Research can be nursing research only when it addresses issues that are relevant to the nursing profession.

•If the topic is not going to have an impact on the nursing practice, it is not nursing research. Thus, it is important to understand that in order to define your research as nursing research; your study must be geared towards improving certain aspects of the nursing practice, education and administration.

•Research is an academic activity and as such the term should be used in a technical sense.

•Research comprises defining and redefining of problems, formulating hypothesis or suggested solutions, collecting, organizing and evaluating, making deductions and reaching conclusions to determine whether they fit the formulating hypothesis

•Research is therefore an original contribution to the existing stock of knowledge making for its advancement.

Classification of research

Research can be classified as follows:

1)Categories, i.e., what the study is to be used for.

2)Methodological approaches, which includes the research approaches that the researcher intends to adapt in the course of the study.

3)Aims of the study, including what the study aims at achieving.

4)The time dimension ,i.e., is the study a ‘one off’ case or one that will take months or even years.

•In broad terms, research can be classified into qualitative and quantitative research approaches.

•The purposes of nursing research include:

–Developing scientific, evidence based reasons for nursing activities.

–Finding ways of increasing the cost-effectiveness of nursing activities.

–Providing a basis for standards setting and quality assurance.

–Providing evidence in support of demands for resources in nursing.

–Barring and defending a professional status for nursing.

–Focusing on priority problems that affect the nursing profession.

CHARACTERISTICS OF GOOD

RESEARCH

•Makes a comprehensive statement and justification of the research problem

•Has clearly stated objectives and research questions

•Measures what it sought to from the onset. If for any reasons this is not possible, the researcher offers plausible explanations for the anomaly

•Has a clearly stated and relevant purpose. For example, if the research focuses on community health, then it must address health areas relevant to the target community and population

•Utilizes an intensive and extensive review of relevant literature to broaden the perspective of the research project

•Clearly and systematically explains the methodology utilized

•Offers plausible interpretations and explanations of the results

•Draws valid evidence-based conclusions deduced from the research results

•Generates plausible evidence based on the scientific methods applied

•Examines the implications of the evidence adduced with other relevant important areas of the target community, such as social, economic, health, policy and other aspects

Answers that a good research should

provide

•What are the perceived health needs of different groups of people?

•To what extent do the present health interactions cover the health priority needs of the people?

•Are the interventions that have been initiated acceptable to the people in terms of culture and cost (especially the poor)? Are these interventions provided as cost-effectively as possible?

•Is it possible to cover more needs given the available resources? Is it possible to expand cost-sharing through insurance? Would this help reduce most of the unexpected high costs?

•Is it possible to better control environmental factors which influence health and health care?

•Can other factors such as education, agricultural, public works or others, be of help?

THE RESEARCH PROCESS

•Has 4 phases;

–The conceptual phase, also called the thinking or planning phase.

–Design and planning phase

–The empirical phase, also called the doing phase.

–The interpretive phase (analytic), or the phase where the researcher looks at the meaning of it all.

–The communication phase or the phase of writing and disseminating the research report

The 4 phases have been expanded to 10 steps

THE RESEARCH PROCESS

1.Identify the research topic

2.Problem statement

3.Rationale/ justification/purpose of the study

4.Formulate research questions, objectives & hypothesis

5.Literature review

6.Research methodology

7.Describe the methods of measurement

8.Data collection and presentation

9.Data analysis & interpretation

10.Communicating research findings, conclusion, recommendations, limitations & appendices

1. IDENTIFICATION OF RESEARCH TOPIC

•This is the first step in developing community health research,

•It provides the focus of the study

•It becomes the title of your Report

The characteristics of a good research topic are:

vIt should be clear and concise. vShould be appealing i.e. attracting

vIt should not contain more than 20 words (including full stops and comas)

vYou can have a title that contains two parts. However, in this case the two parts have to be separated by a colon (:)

Example of a title consisting of two

parts

AN ASSESSMENT OF FACTORS INFLUENCING IMPLEMENTATION OF THE HIV/AIDS EDUCATION CURRICULUM IN PRIMARY SCHOOLS: A CASE STUDY OF NAIROBI PROVINCE

CRITERIA FOR TITLE SELECTION

•Should be of your own choice

•One that provides focus for a study you want to undertake

•A researcher may draw research topics from:

–Existing professional knowledge and experience.

–Socially significant issues i.e., the research topic has practical relevance and significance to the society. For instance, the study could be in a position to solve an existing and pressing social problem.

–A study that has scientific relevance and significance as well. It is important to show that the research will, at the end, have academic and/or scientific relevance.

2. PROBLEM STATEMENT

INTRODUCTION

•The next defines clearly the problem you propose to examine

t step after topic selection is the statement of the problem.

•This provides the context for your research

•It explains why it is important to carry out the research

•A brief review of literature will be required in delineating and defining the research problem

DEFINITION OF PROBLEM STATEMENT

•The problem statement is a specific statement that clearly conveys the scope, magnitude and purpose of the research study.

Reasons why it is Important to State and Define the Problem Well

•Is the foundation for further development of the research proposal (research objectives, methodology, work plan, budget)

•Makes it easier to find information and reports of similar studies from which your own study design can benefit

vEnables you to systematically point out:

•why the proposed research on the problem should be undertaken and

•what you hope to achieve with the study result. This is especially important when you have to present your project to community members, health staff, relevant ministries and donor agencies that need to support your study or give their consent

•It important when you have to present your project to community members, health staff, relevant ministries and donor agencies that need to support your study or give their consent

iv)Concerted efforts must be made to establish

–How wide spread is the problem?

–Who is affected by the problem?

–What is its distribution?

–How often does the problem occur?

–What social or cultural practices are associated with the problem?

–What costs are associated with the problem?

v)A thorough literature review would assist in determining the following:

•Incidence and prevalence of the problem;

•Geographic areas affected by the problem;

•Population affected by the problem;

•Probable reasons for the problem;

•Possible solutions;

•Unanswered questions that need to be researched.

SUMMARY OF A WELL STATED

PROBLEM

A well-defined research problem statement leads naturally to the statement of:

•research objectives,

•hypotheses;

•definition of key variables, and

•selection of a methodology for measuring the variables

NOTE: A poorly defined research problem leads to confusion

Procedure for Identifying and Defining

a Research Problem: Step 1

•Problem situation: Start with a simple statement of the problem situation. Write a small simple paragraph that identifies the problem.

•Discrepancy: State what the discrepancy is between what is and what should be.

•Problem Question: Write down the central problem question.

•Possible answers: Write two or more plausible answers to the problem question

STEP 2

•Add details as you review the literature, review theoretical concepts and investigate the problem in greater depth. Try to answer the following questions:

–What is the incidence and prevalence of the problem?

–What geographic areas are affected by the problem?

–Which population groups are affected by the problem?

–How was the problem studied in the past?

–What are the findings from other research studies?

–What has been done to overcome the problem?

–What seems to be the major unanswered questions about the problem?

Step3

•Simplify the focus by identifying the most important aspects of the problem that are researchable.

Step4

•Let one or more colleagues review your final statement identifying and defining the problem. Revise your statement if necessary in the light of the comments and suggestions received.

Information to be Included in the

Statement of the Problem

•A brief description of the socio-economic and cultural characteristics and an overview of the health status and health care system in the study area in as far as these are relevant to the research problem. Include a few illustrative statistics, if available to help describe the context in which the problem occurs

•

•A concise description of the nature of the problem (the discrepancy between what it is and what it should be) and its magnitude, distribution, and severity (who is affected, where, since when, and what are the consequences for those affected and for the services?)

•An analysis of the major factors that may influence the problem and a convincing argument that available information and knowledge is not sufficient to solve the problem.

•A brief description of any solutions that have been tried in the past, how well they have worked and why the further research is needed.

•A description of the type of information expected to result from the research and how this information will be used to help solve the problem

CHARACTERISTICS OF A GOOD PROBLEM STATEMENT

•It is written clearly and attracts the reader’s interest;

•It has identified a specific problem which is researchable

•It spells out the scope of the research problem

STEP 3: RATIONALE/JUSTIFICATION OF

THE RESEARCH PROBLEM

•After stating the research problem is to justify why you chose to study this problem.

•The words ‘rationale’ and ‘justification’ are commonly used interchangeably.

•This is the section of the study that outlines reasons for carrying out the study.

•Justifications of the study should address some of the following questions( QUESTIONS THAT YOU

MUST ADDRESS):

vIs the problem you wish to study a current and timely one? Does it exist now?

vHow widespread is the problem? Are many areas and many people affected?

vDoes the problem affect key populations such as the adolescents, youth, expectant mothers or children?

vDoes the problem relate to ongoing intervention activities?

vDoes the problem relate to broad social, economic and health issues such as poverty, status of women, or education?

vWho else is concerned about the problem? Are top government officials concerned? Are health and other professionals concerned?

vWhat gaps in knowledge do you want to fill in and why is it important to generate information to fill those gaps?

•It is important to state the justification convincingly so as to rationalize the utilization of resources such as time, money materials and manpower.

•The rationale of the study should describe the utility and importance of the problem in health care services in general and the nursing profession in particular.

AREAS YOU NEED TO JUSTIFY

•You will also need to justify the location or site(s) in which to conduct your research.

•The location or site must be described in some detail, paying attention to its appropriateness to the research proposed.

STEP 4: Formulation of Research questions,

Objectives and Hypothesis

What are RESEARCH QUESTIONS?

•These are questions whose answers should help us come up with a solution to the problem stated.

•Answers to these questions will be obtained through the research you will conduct

HOW TO FORMULATE RESEARCH QUESTIONS

•The research question (s) should develop logically from the problem and context you have defined under the introduction and problem statement section and

•should describe the core objective of your research.

•These are the most important questions whose answers you are seeking to find through your research

Research question assists the researcher to:

a)Focus on the study by narrowing it down to the essentials

b)Avoid collection of data that are not necessary

c)Organize the study in clearly defined parts or phases

Example of a research question

•An example of a research question might be: "What is the relationship between Allergic conjunctivitis and age"?

RESEARCH OBJECTIVES

Def: A research objective is a clear, concise, declarative, statement expressed to direct a study. It focuses on identification and description of variables and/or determination of the relationships among variables.

•Objectives describe the expected results arising from the study

•Usually broad and specific objectives are stated

Importance of research objectives

•Research objectives help to:

a)Bridge the gap between the research purpose and the study design.

b)Guide on planning for data collection and analysis.

c)Summarize what is to be achieved by the study.

d)Build a close link with the statement of the problem.

e)Keep the researcher within the scope of study by defining the area of focus.

•Research objectives are sub-divided into broad and specific objectives. When formulating good research objectives, the objectives should have the following characteristics, using the acronym ‘SMART’

Note: Your research objectives should develop logically from your research questions and the problem stated

CATEGORIES OF RESEARCH

OBJECTIVES

•Broad

•Specific

Broad Objectives

•describe the expected contributions arising from the study.

•relate the reasonable and expected contributions of the study to broad social, economic, or health concerns

•contribute to the justification of why research on the problem is required

NOTE

•Note that broad objectives are the expected contributions.

•The investigator does not promise that the contribution will occur and therefore, usually does not try to measure them.

Guidelines for writing research

objectives

The writing of the broad objectives will be guided by the following questions:

•How will the results from the study help improve service delivery, improve training programs, or assist in the design of educational materials?

•In other words, what are the anticipated contributions of the study

EXAMPLES OF BROAD OBJECTIVES

•The broad objective of this study is to contribute towards increasing utilization of RH services among Kenyan adolescents.

•The broad objective of this study is to contribute towards reduction of the prevalence of Malaria among the study population.

•The broad objective of this study is to contribute to a better understanding of the factors that affect the use of maternal health care services in the study area

SPECIFIC OBJECTIVES

•In contrast to broad objectives that state what is expected to happen, specific objectives relate directly to the research problem situation.

•These are the outputs or deliverables of the study for which the researcher is responsible

•They indicate the variables that will be examined and measured.

•An immediate objective represents a promise by the investigator that certain specific variables will be examined

•Specific objectives are expressed in measurable terms

EXAMPLES OF SPECIFIC OBJECTIVES

•To establish the influence of education on the use of treated mosquito nets in the study area.

•To establish the association between the attitude of health workers and client satisfaction in the study area.

•To identify the effect of public health education campaign on the uptake of modern maternal health care services.

•To establish the effect of staff training on the quality of care provided and client satisfaction

HYPOTHESIS OF THE STUDY

Description:

•This is a statement about an expected relationship between two or more variables that permits empirical testing

•It is the researcher’s prediction or explanation of the relationships between two variables. E.g.

-Persons with Type II diabetes mellitus who have greater knowledge of their diseases will have a higher rate of adherence to treatment regimen than those with less knowledge.

Difference between Specific objectives, Broad objectives and hypothesis

•While broad objectives identify the anticipated contributions arising from a study,

•and specific objectives specify what will be done or measured in the study,

•hypotheses specify the expected relationship among the variables

Where are hypothesis required?

•They are most appropriate for field intervention or evaluative studies.

•Diagnostic or exploratory studies do not normally require hypotheses because they generally do not test relationships between variables.

WHY HYPOTHESES ARE IMPORTANT?

•Study hypotheses serve to direct and guide the research.

•They indicate the major independent and dependent variables of interest.

•They suggest the type of data that must be collected and the type of analysis that must be conducted in order to measure the relationship among the variables

TYPES OF HYPOTHESES

1.Directional Hypothesis: it predicts an outcome in

a specific direction. Example;

Persons with Type II diabetes mellitus and have greater knowledge of their diseases will have a higher rate of adherence to treatment regimen than those with less knowledge.

2.Non Directional Hypothesis: it indicates there is a difference or correlation but does not specify which. For example:

Persons with Type II diabetes mellitus who follow a structured programme on their condition have a higher rate of adherence to treatment.

•This does not indicate a directional relationship.

•Null Hypothesis and Alternative Hypothesis 1) Null hypothesis (denoted as H0): The null (statistical) hypothesis is used for statistical testing and interpretation. It states no difference exists between groups or no correlations between variables. Example;

There is no difference in performance of national examinations between standard eight pupils from rural primary schools and standard eight students from urban

primary school in Kenya.

2)Alternative hypothesis (denoted as H1): It states that there is a difference or correlation.

Considerations in Writing the

Hypothesis

•In writing study hypotheses, always think in terms of the expected relationship between variables

HOW TO WRITE A HYPOTHESIS

•Think first about the central problem your study will address (the dependent variable).

•Next, consider what factor or factors (the independent variables) might cause, determine, or influence the dependent variable

•Finally, ask yourself if the relationship between the independent and dependent variables is direct or indirect through a set of intervening variables.

VARIABLES

Def: Variables are defined as quality, properties or characteristics of persons, things or situation that change or vary. For example: sex (male and female) age (20–25, 26–30 years) academic success, stress and pain.

Types of variables

1)Independent Variable(treatment/experimental) It’s a variable that influences other variables.

It is perceived as contributing to or enabling a particular outcome.

•Independent variables usually describe what the researcher wishes to measure in order to determine its effect on an observed phenomenon (the dependent variable)

–It is the intervention or treatment that the researcher performs to see the resulting change in the dependant variable. It is also referred to as the input.

2)Dependent Variable: This is the outcome variable. It reflects the effects (outcome) or response to the independent variable.

It is the variable that appears, disappears, diminishes or increases.

it describes the problem under study

For example, to determine the effects of salt intake on hypertension, the blood pressure is the dependant variable and salt intake is the independent variable.

3)Extraneous Variables: These are uncontrolled variables that influence the findings of the research study. They include intervening, antecedent, suppressor, and distorter variables.

They influence both the dependent and independent variables. These are called threats to internal and external validity of the study and may bias the selection, the time factor, and the instrument used.

4)Demographic Variables :These are demographic attributes. They are variables that cannot be manipulated or influenced by the researcher, for example, age, sex religious beliefs or educational level

5)Control variables: If a researcher suspects that a certain variable is likely to influence the research results, he or she should control for that variable (the extraneous) in the study.

•When an extraneous variable is built into the study, it is referred to as a control variable. Some researchers refer to control variable as concomitant, covariate, or blocking variables.

•The introduction of a control variable in research study increases the validity of the data and therefore it leads to more convincing generalizations.

For example, if gender may also influence reaction time, we should add sex as an independent variable in our study. Using a statistical procedure such as regression, we can measure the effect of alcohol on reaction time, controlling for sex.

6)Intervening variable: The logical status of an intervening variable is that it is recognized as being caused by the independent variable and as being a determinant of the dependent variable. i.e.

Independent intervening dependent

variable variable variable

•An intervening variable comes in between the independent and the dependent variables.

•When intervening variable are used as control variables, one must establish the dominant direction of influence.

•The independent variable influences the intervening variable and the intervening variable influences the dependent variable.

STEP 5: LITERATURE REVIEW

Description: is a summary of theoretical and empirical sources to generate a picture of what is known and not known about a particular problem.

•This is a systematic review of existing information (literature) about a specific subject or topic.

•This is sometimes referred to as desk or library research.

•The information could be published such as journal articles and books or unpublished such as research reports or monographs.

•This review is usually undertaken by the researcher himself or herself or by a team.

Literature review entails;

•The history of the problem

•The magnitude & distribution of the problem, including the population being affected

•The severity of the problem

•Methodology (ies) used in the previous studies

•Theoretical and analytical frameworks used

•Hypotheses and variables used and their measurements

•Research Designs used

•Methods of data collection used

•Sampling procedures and sample sizes used

LITERURE REVIEW ENTAILS CNTD’

•Main findings of the previous researches or studies

•Main conclusions and recommendations of previous studies

•Past efforts to solve the problem

THE MAIN PURPOSES OF LITERATURE REVIEW ARE TO:

1.Determine what has been done already as regards the research problem under investigation.

2.Identify strategies, procedures and measuring instruments that have been found useful in the investigation of the research problem.

3.Help make the researcher familiar with previous studies and thus facilitate the interpretation of the study.

4.Help the researcher to narrow the research topic.

5.Help determine new approaches and stimulate new ideas

When reviewing any literature, the researcher needs to:

1.Assess the strengths and weaknesses of past work on the subject

2.Report any inconsistent findings

3.Identify gaps in the knowledge

4.Determine the contribution of proposed study

5.Consider the possibility of unintentional duplication

Steps in carrying a Literature Review

•Be familiar with the library

•Make a list of key words or phrases to guide the review

•With the key words/ phrases go to the library. Lib staff are always ready to help

•With the key words/ phrases go to the computer internet and do a search

•Summarize references on cards for easy organization

•Analyze, organize and report in an orderly manner

•Make an outline of main topics/ themes, headlines and sub-titles

•Studies with contrary views should not be ignored. Attempt to account for the differences in opinion

•The more general literature should be covered first before narrowing to what is more specific to the research problem –this paves way for identifying testable hypotheses

Primary Source This is the work written by the person who is actually involved in, or is responsible for, the generation of the

idea published.

•It can also be information from a person who actually observed or witnessed the occurrence under investigation.

•The person who conducts empirical research and publishes it in a journal is usually regarded as the primary source of information

Secondary Source :involves summaries or quoted content from a primary source.

•This type of work is usually a paraphrase of the primary source. Often, it does not give the correct interpretation of the primary sources.

•It is usually information given by someone who was not a direct observer or participant of the events described.

Sources of secondary information

1.Scholarly Journals

2.Theses and Dissertations: research projects written by Masters and PhD students.

3.Govt. Documents; i.e. policy papers, research reports owned by the govt., annual reports of hospitals and government ministries

4.Papers Presented at Conferences

5.Books

6.Computers: Computers also have databases prepared for literature search. Examples of such databases are MEDLINE or INDEX MEDICUS, Pub Med

TIPS ON GOOD REVIEWING OF LITERATURE

•Do not conduct a hurried literature review. You are likely to overlook important issues

•Do not rely too heavily on secondary sources. Try to get some primary information from experts, opinion leaders, peers etc

•Do not concentrate only on findings. Read the methodology and measurement of variables also

TIPS ON GOOD REVIEWING OF

LITERATURE cntd’

•Check daily newspapers –educative and current information

•Copy references correctly so as to avoid frustration of trying to retrace a reference later

PLAGIARISM

•“The substantial use, without acknowledgement and with intend to deceive the examiners or knowing that the examiners might be deceived, representing, whether by copying or paraphrase, the ideas or discoveries of another or of others as one's own work submitted for assessment.

•The mere inclusion of the source in a bibliography shall not be considered sufficient acknowledgement”

HOW TO AVOID PLAGIARISM

•Summary- In your own words and cite reference

•Paraphrase- Translate source into your own words and cite reference

•Quotation- Word-for-word and cite reference

STEP 6: RESEARCH METHODOLOGY

•Every researcher has to identify an appropriate research design for use in the study. Identification of a specific study design will depend on :

–Available information (state of knowledge) about the problem.

–The nature of the problem and its environment.

–The availability of resources for the study.

–The skills and creativity of the researchers.

Types of research designs

•Experimental Design: Experimental and Quasi- experimental.

•Survey Design: Comparative and Correlation.

•Descriptive Design: Descriptive and Explorative.

•Case Study Design

1.Experimental Research Design

Commonly used in clinical settings because of its accuracy and reliability.

It could be subdivided into true experimental and quasi-experimental.

Characteristics of experimental research design

Manipulation: the researcher controls the independent variable, which can be an event, intervention or treatment that is expected to have some effect on the dependant variable.

Control :The researcher exercises control over the experimental situation by eliminating the actions of other possible variables beyond the independent variable.

Randomizing : Every subject is given an equal chance to participate in the study. The researcher assigns the subjects to the experimental or control groups on a random basis.

•In a quasi-experimental design, some of the above rules are relaxed. For example, there might be no need for having a control group or at times randomization may not be included. The quasi- experimental design enables the search for knowledge and examination of causality in situations where complete control is not possible.

Advantages

1.Most powerful design for testing the hypothesis of cause-effect relationships between variables.

2.It is practical, feasible and can be generalized to some extent. This type of design introduces some control over certain extraneous variables.

Disadvantages

1.In most real situations, it is difficult to conduct a true experimental design, since some of the variables cannot be manipulated or controlled.

2.At times it becomes quite difficult to get randomized research subjects or even a control group.

3.As a result of the need for randomization, control and manipulation with the aim of establishing cause-effect relationships, the design becomes very expensive, both in terms of time and money.

2.Survey Research Design

•Is the systematic gathering of information. Survey studies are concerned with gathering information from a sample of population.

•The purpose of the study is usually to identify general trends or patterns in the collected data.

•It’s designed to obtain information from the population regarding the prevalence, distribution, and interrelations of variables within those populations.

•Survey studies primarily yield quantitative data. They are mainly cross sectional in design.

•They mainly deal with (investigate) what people do, for example, how or what they eat, how they meet their health needs, what kind of family planning behaviour they engage in and so on.

Advantages

1.It is flexible and broad in scope.

2.It can be applied to many people

3.It can focus on wide range of topics

The survey design is better suited for extensive rather than intensive analysis of a situation.

It is usually descriptive and specific based on the situation that needs intervention, for planning purposes, monitoring and evaluation of services.

•In a survey the researcher designs the phenomenon and study but does not manipulate any variables nor do they make any efforts to determine the relationships between variables.

•In the correlation survey meanwhile, the researcher attempts to determine and describe what relationship exists between variables.

•One independent variable is correlated with one or more dependent variables. Then statistical methods are applied to describe if the variables relate at all and what kind of relationship they have, that is, positive correlation or, negative correlation

•When there is a positive correlation is an indication that the more the exposure the high the outcome of interest, for example smoking exposure and lung disease, which is the outcome.

•When there is no correlation one would conclude that the exposure is not related to the outcome, for example teething and diarrhoeal episodes.

•When there is a negative correlation it means that the more the exposure the less the outcome, for example tetanus vaccination and tetanus infection.

3. Descriptive or Explorative Research Design

•Is the systematic collection and presentation of data to give clear picture of a particular situation.

•It involves the systematic collection of information and aims to discover and describe new facts about a situation, people, activities, or events.

•Its main purposes include observing, describing and documenting all aspects of a situation as it naturally occurs.

•At times, descriptive designs are used as a starting point for hypothesis generation or theory testing.

•In the exploratory descriptive design, the main purpose is to explore the dimensions of a phenomenon (problem) as well as the major characteristics or facts that influence the phenomenon.

•In descriptive design, no manipulation of variables is involved as opposed to experimental design.

•Similarly, no dependent or independent variables are used because no attempt is made to establish causality. The overall purpose of descriptive research is to provide a picture of a phenomenon as it naturally occurs, as opposed to studying the impacts of the phenomenon or intervention.

Categories of descriptive research design

1.Explorative Descriptive Design: the researcher explores a particular problem to discover what is there and if it could be solved. The study focuses on new events, evidence, or practices.

2.Simple Design: Is mainly a follow up of an

exploratory design. The variable of interest has already been identified. It is used when the researcher intends to examine only a single problem.

3.Comparative Descriptive Design: Is mainly used when the researcher intends to examine and describe particular variables in two or more groups. The concept here is to compare the groups and how they differ or how similar they are in relation to the variable of interest.

4.Time Dimensional Designs: Are used in epidemiological studies and are further sub-divided into longitudinal that is when it examines changes in a group for a long period and it is cross-sectional where the data is collected at one point in time.

5.Retrospective Study Design: Also known as 'export facts'. It is a study design aimed at a looking back in order to link the present with the past or what happened in the past.

6.Prospective Study Design: Is similar to the longitudinal study as it starts from the present and ends by looking into the future. It is further divided into two categories: descriptive and explanatory.

•The subjects for the study are recruited based on presence or absence of an exposure of interest (workers in x-ray department) and followed up over many years to establish if they will develop outcomes of interest, for example cancer of the skin or reproductive health complications.

Features used to diff. types of descriptive res. design

1.Representativeness of the study data sources, for example, whether random, stratified, non probability.

2.Time frame of measurement, i.e., whether short, cross sectional or longitudinal.

3.Whether the study involves any comparisons, for example, with another group.

4.Whether the design is focused on a simple descriptive question or more complex, correlative questions.

strengths	weakness
Lower costs	Does not answer questions
	of causal-effect relationship
	nature
Relatively easy to implement	Expensive when complex
	data collection techniques
	are used
Ability to yield results in	May not consider variables
fairly short period	in depth
Results are relatively	Generalizability of the
straightforward to analyze	findings may not be achieved
and communicate to
an audience

4.Case Study Research Design

•A case study is 'an in depth study of one individual, a group of individuals or an institution’

•It is a detailed account of a particular experience event or situation.

•It is meant to provide a description of people’s thoughts, feelings and perceptions.

•It doesn’t aim at providing a causal relationship. Neither does it attempt to test a hypothesis.

For example, a case study on why in a certain health centres mothers are not coming in for their antenatal services.

Limitations of case studies

1.They require plenty of time.

2.They are costly.

3.Have high possibility of subject drop out.

4.Data analysis also calls for skills and experience, particularly if the study is carried over a long period of time

•Case study designs are used when:

1.There is a need to demonstrate the effectiveness of a specific therapeutic technique

2.Generating and testing hypotheses

3.There is need to generate knowledge on a particular issue or situation that has not been adequately researched on

QUALITATIVE RESEARCH

•What is qualitative research?

–Qualitative research is a field of inquiry that cross- cuts disciplines and subject matters.

–It involves in-depth understanding of human behaviour and the reasons that govern human behaviour.

–It relies on reasons behind various aspects of behaviour. It focuses on understanding, rather than predicting or controlling phenomena.

–It investigates the ‘why’ and ‘how’ of decision making

Distinction between qualitative and

quantitative research

Quantitative	Qualitative
what	why
Where	how
when

CHARACTERISTIC	QUANTITATIVE RESEARCH	QUALITATIVE RESEARCH
Philosophical Origin	Logical Positivism	Naturalistic, Interpretive,
		Humanistic
Focus	Concise, Objective,	Broad, Subjective, Holistic
	Reductionistic
Reasoning	Logical, Deductive	Dialectic, Inductive
Basis Of Knowing	Cause-Effect Relationship	Meaning, Discovery,
		Understanding
Theoretical Focus	Tests Theory	Develops Theory
Researcher Involvement	Control	Shared Interpretation
Methods Of Measurement	Structured Interviews,	Unstructured Interviews And
	Questionnaire, Observations,	Observations
	Etc
Sample Size	Predetermined	Determined At Saturation
Data	Numbers	Words
Analysis	Statistical	Individual Interpretation
Findings	Generalization, Accept Or	Uniqueness, Dynamic,
	Reject Theoretical	Understanding Of
	Propositions	Phenomena, And New Theory

BASIC TERMS IN RESEARCH

METHODOLOGY

•Population: refers to an entire group of individuals, events or objects having a common observable characteristic. It is an aggregate of all that conforms to a given specification

•The researcher first defines the population to which she or he wants to generalize the results. This is referred to as the “target population or the “universe”.

•Sample: is a smaller group obtained from the accessible population. Each member or case in this sample is referred to as “subject”. Sometimes, the terms “respondents” or interviewers” are used.

•Sampling: the process of selecting a number of individuals for a study in such a way that the individuals selected represent the large group from which they were selected.

–The purpose of sampling is to secure a representative group which will enable the researcher to gain information about the population

ADVANTAGES OF SAMPLING

•Research can be done more quickly,

•less expensively,

•and often more accurately than a large census (survey of the entire population).

•In fact, given limited research budgets and typically large population sizes, there is usually no alternative but to do sampling.

•Variable: is a measurable characteristic that assumes different values among the subjects. It is a logical way of expressing a particular attribute in a subject. Some attributes are expressed quantitatively. E.g., age is expressed in years,

–Other variables are expressed in categories, e.g. occupation may be expressed as farmer, teacher

•Conceptual or theoretical definition of variables: it is a way of specifying precisely what we mean when we use a particular term to refer to a variable. I.e. the working definition of the variable.

•Operational definition of variables: refers to the measurement of a variable. It is the description that will be used in measuring a variable

•Data: refers to all the information a researcher gathers for his or her study. There are 2 types of data:

–Primary data: refers to the information a researcher obtains from the field.

–Secondary data refers to the information which a researcher obtains from research articles, books, casual interviews.

•Data may also be classified as quantitative (numerical) or qualitative (words or phrases).

•Parameter: like a variable it is a characteristic that is measurable and can assume different values in the population. The difference between a parameter and a variable is that a parameter refers to a population characteristic while a variable is related to a characteristic of a sample drawn from the population.

•Sampling Frame: Is a comprehensive list of all the sampling elements in the target population, for example, the list of nurses working in a particular district, the number of under five children in a village or all the households in a village.

•Representative Sample: the sample that resembles the population from which it is drawn in all aspects. It should possess all the variables a researcher is interested in, for example, educational level, socioeconomic factors etc.

•Sampling Bias: Occurs when the researcher has not carefully selected the samples that are expected to represent the general target pop.

•Sampling Error: Refers to the difference between population parameters (for example, the average age of the population) and the sample statistics (for example, the average age of the sample group). It is the degree of deviation of the sample from the population from which it was drawn.

Sampling Techniques 2 types

–Probability or random sampling

–Non probability sampling

Probability Sampling

•Allows for a much more a representative sample of the population and enables the estimation of sampling error.

•It also enables the calculation of differential statistics and allows the study to be generalized to other areas.

•It involves a random selection procedure to ensure that each unit of the sample is chosen on the basis of chance.

•All units of the study population have an equal or at least a known chance of being included in the sample from list provided

Probability Sampling Techniques

1.Simple Random Sampling: one of the commonest and the simplest methods of sampling.

•Each unit (subject) has the chance to be selected.

•It involves one stage selection. It also allows the researcher access to the study population

•There are several ways of selecting a random sample using this technique. These include, the lottery method, use of random tables, or tossing a coin to help you decide where and how to start.

2.Systematic or Interval Sampling: is the selection of every nth element from a sampling frame, where n, the sampling interval, is calculated as:

•n = number in population/number in sample

•Each element in the population has a known and equal probability of selection.

•It is much more efficient and much less expensive to do than simple random sampling.

3.Stratified Random Sampling: When sub- populations vary considerably, it is advantageous to sample each subpopulation (stratum) independently.

Stratification is the process of grouping members of the population into relatively homogeneous subgroups, e.g., by education level, before sampling.

The strata should be mutually exclusive, i.e., every element in the population must be assigned to only one stratum.

•The strata should also be collectively exhaustive, that is, no population element can be excluded.

•Random sampling is then applied within each stratum. This often improves the representativeness of the sample by reducing sampling error.

4.Cluster Sampling: Is a sampling technique used when 'natural' groupings are evident in the population.

The total population is divided into these groups (or clusters), and a sample of the groups is selected. The required information is then collected from the elements within each selected group.

•This may be done for every element in these groups, or a subsample of elements may be selected within each of these groups.

•Elements within a cluster should ideally be as homogeneous as possible. However, there should be heterogeneity between clusters.

•Each cluster should be a small scale version of the total population. The clusters should be mutually exclusive and collectively exhaustive.

•A random sampling technique is then used on any relevant clusters to choose which clusters to include in the study.

5.Multi-stage random Sampling

•Sometimes, when populations are extremely complex, it is necessary to go beyond the two stages in cluster sampling, and use a technique referred to as multi-stage cluster sampling.

•For example, if you want to carry out a survey on safe motherhood in a particular district but do not have a list of households or women in the reproductive age.

•You might have to begin with a random sample of divisions, then do a random selection of locations in each of the selected divisions, then random sample sub-locations in each selected location, than random sample villages in each selected sub-location and when you arrive at each village, make a list of households and draw a random selection of households to visit

•When you arrive at a household, you would randomly select a woman to interview, or interview all eligible women.

•In either case, you would apply a sampling fraction to each village, such as one out of five households or one out of ten eligible women.

Non Probability Sampling

•This type of sampling is used for interventional studies.

•Non-probability sampling refers to the selection of a sample that is not based on known probabilities.

•It is distinguished from probability sampling by the fact that subjective judgment plays a role in selecting the sampling elements.

•When the probabilities of selection are not known, there is no precise way to adjust for such distortions.

•Despite these drawbacks, there are many instances in which obtaining a truly representative probability sample may be too difficult or too expensive.

•In fact, much of health research uses some kind of non-probability sampling.

•For example, it is usually necessary to use non -probability samples when studying sex workers and their clients, injecting drug users, gay men and lesbians

1.Purposive or Judgmental Sampling: it is where the researcher selects a particular group or groups based on certain criteria.

•In this method the researcher determines who should be included in the study. It is, in fact, the researcher’s opinion that the sample is representative of the target population. Commonly used in qualitative studies.

Advantage: it gives the researcher a free hand to respond according to their judgment.

Disadvantages:

Øsampling biases,

Øthe possibility of unrepresentative samples.

Ølack of generalizations of the study findings.

2.Quota Sampling: The population is first segmented into mutually exclusive sub-groups, just as in stratified sampling.

•Then judgment is used to select the subjects or units from each segment based on a specified proportion.

3. Convenience or Accidental/Availability Sampling

•The researcher is unable to control bias at all. The study units that happen to be available at the time of data collection are selected and used as a sample. This type of sampling allows the utilization of any available target population.

e.g., if you need to assess the BP of females using depo provera who are above 40 years of age, you will need to check the blood pressure of any female patient above this age irrespective of her parity or other characteristics.

4.Snow Ball Sampling: it is a technique for developing a research sample where existing study subjects recruit future subjects from among their acquaintances. Thus, the sample group appears to grow like a rolling snowball.

•This sampling technique is often used in hidden populations which are difficult for researchers to access. E.g. populations include drug users and commercial sex workers.

•Sample members are not selected from a sampling frame, therefore, snowball samples are subject to numerous biases.

SAMPLE SIZE DETERMINATION USING FISCHER’S STATISTICAL FORMULA

•In social science research, the following formula can be used to determine the sample size? FISCHER’S formula

Z2 pq

n =

d2

Where:

n = the desired sample size (if the target population is greater than 10,000)

z = the standard normal deviate at the required confidence level, usually set at 1.96 which corresponds to the 95% confidence level

p = the proportion in the target population estimated to have characteristics being measured.

q = the proportion in the target population estimated not to have characteristics being measured=1-p

d = the level of statistical significance/ degree of accuracy desired, usually set at the 0.05 level

•If there is no estimate available of the proportion in the target population assumed to have the characteristics of interest, 50% should be used as recommended by Fischer’s et al.

•For example, if the proportion of a target population with a certain characteristic is 0.50, the Z statistic is 1.96, and we desire accuracy at the 0.05 level, then the sample size is

n=	(1.96)2 (0.50) (0.50)	= 384.16
	(0.05)2

•If the target population is less than 10,000, the required sample size will be smaller. In such cases, calculate a final sample estimate (nf) using the following formula:

n

nf = {1+ (n/N)}

Where:

nf = the desired sample size (when the population is less than 10,000)

n= the desired sample size (when the population is more than 10,000).

N = the estimate of the population size

STEP 7: METHODS OF MEASUREMENT

1.Review of Existing Records Advantages.

a)saves time and money

b)Limits respondent bias. Existing data utilizes records, which are unbiased, as the person who collected the data had no knowledge of the future use to which it would be put.

c)They cover a long period of time, which is particularly useful to the researcher who can only dedicate a short time to their research.

d)Saves the researcher from the worries and concerns of seeking the cooperation of the respondents.

Disadvantages

•Since the researcher is not responsible for the collection and recording of the data, limiting biases and even ascertaining the authenticity of the data would be difficult. This can often result in doubts about the validity of the data.

2. Structured Interview Schedule

It is a formal and written document where questions are asked orally in either face-to-face or telephone interviews.

The responses are then recorded by the researcher

Advantages

1.It provides comparability of responses and facilitates analysis.

2.Good for measuring attitudes and most other content of interest.

3.Allows probing and posing of follow-up questions by the interviewer.

4.Can provide in-depth information.

5.Can provide information about participants’ internal meanings and ways of thinking.

6.Closed-ended interviews provide exact information needed by researcher.

7.Telephone and e-mail interviews provide very quick turnaround.

8.Moderately high measurement validity (i.e., high reliability and validity) for well constructed and tested interview protocols.

9.Also applicable to a special category of respondents, such as children, the elderly and the illiterate who may not be able to read and write.

10.Useful for exploration as well as confirmation.

11.The instrument is expected to have a high response rate, since the researcher administers it personally.

12.An interview schedule also has the advantage of capturing the respondent’s own words.

Disadvantages

1.The instrument demands a much longer time to complete than other instruments, such as questionnaires.

2.Due to the presence of the researcher, respondents may withhold certain vital information or even change information to please the researcher- Reactive effects

3.In-person interviews usually are expensive and time consuming.

4.Investigator effects may occur (e.g., untrained interviewers may distort data because of personal biases and poor interviewing skills).

5.Interviewees may not recall important information and may lack self-awareness.

6.Perceived anonymity by respondents may be low.

7.Data analysis can be time consuming for open- ended items.

8.Measures need validation.

•Key informant

•Def: a person (or group of persons) who has unique skills or professional background related to the issue/intervention being evaluated, is knowledgeable about the project participants, or has access to other information of interest to the evaluator.

•Can also be someone who has a way of communicating that represents or captures the essence of what the participants say and do.

•Advantages

1.Information concerning causes, reasons, and/or best approaches from an "insider" point of view.

2.Advice/feedback increases credibility of study

3.Pipeline to pivotal groups

4.May have side benefit to solidify relationships between evaluators, clients, participants, and other stakeholders

•Disadvantages

1.Time required to select and get commitment may be substantial

2.Relationship between evaluator and informants may influence type of data obtained

3.Informants may interject own biases and impressions

4.May result in disagreements among individuals leading to frustration/ conflicts

3. Focus Group Discussions

•They are interviews with groups of 5-15 people whose opinions and experiences are solicited simultaneously.

•The composition of the group is usually limited to those with similar characteristics, such as socio- economic status, so that the members feel free in contributing to the issue at hand.

•It is efficient and can generate dialogue

•The instrument allows the members to share their views, experiences and opinions.

•The interpersonal interactions create a free and enjoyable environment.

Advantages

1.Allows a large number of respondents to be interviewed at one go, which saves time and money.

2.Useful for exploring ideas and concepts.

3.Provides window into participants’ internal thinking.

4.Can obtain in-depth information.

5.Can examine how participants react to each other.

6.Allows probing.

7.Most content can be tapped.

8.Allows quick turnaround.

Disadvantage

1.Because of the number of respondents involved, calls for diligence and skill in ensuring that the process runs smoothly and yields the desired information.

2.Sometimes expensive.

3.May be difficult to find a focus group moderator with good facilitative and rapport building skills.

4.Reactive and investigator effects may occur if participants feel they are being watched or studied.

5.May be dominated by one or two participants.

6.Difficult to generalize results if small, unrepresentative samples of participants are used.

7.May include large amount of extra or unnecessary information.

8.Measurement validity may be low.

9.Usually should not be the only data collection methods used in a study.

10.Data analysis can be time consuming because of the open-ended nature of the data.

4. In-depth Interviews (unstructured interview)

It utilizes face-to-face in-depth interviews using semi-structured questionnaires for key informants.

Key informant interviews are defined as interviews with people who have special positions in the community and whose opinions and experiences are seen as representative of a whole group.

Advantages

1.Semi-structured questionnaires possess a flexibility that allows the researcher to gather in depth information.

2.The instrument enables the participants to give responses in a narrative form and is quite useful in qualitative research.

3.The respondent takes the lead and determines the flow of the conversation, which is of great importance when new areas are to be investigated.

4.Key informant interviews provide valuable and independent information about the research population within a short span of time and save time and money.

Disadvantage

It requires the researcher to be very articulate.

5. Non Participatory Structured Observation

•It is observing a given situation from the outside.

•The observer declares their intention to observe and goes ahead to watch the activities being carried out without asking questions or interfering in any way.

•As the activities to be observed progress, the obse- rver remains in the background, keenly observing and noting down events without comment.

•It provides the in-depth and variety of information.

•The observers are used as measuring instruments and provide a uniquely sensitive and intelligent tool.

Advantages

1.Allows one to directly see what people do without having to rely on what they say they do.

2.Provides firsthand experience, especially if the observer participates in activities.

3.Can provide relatively objective measurement of behavior (especially for standardized observations).

4.Observer can determine what does not occur.

5.Observer may see things that escape the awareness of people in the setting.

6.Excellent way to discover what is occurring in a setting.

7.Helps in understanding importance of contextual factors.

8.Can be used with participants with weak verbal skills.

9.May provide information on things people would otherwise be unwilling to talk about.

10.Observer may move beyond selective perceptions of people in the setting.

11.Good for description.

12.Provides moderate degree of realism (when done outside of the laboratory).

Disadvantages

1.Reasons for observed behavior may be unclear.

2.Reactive effects may occur when respondents know they are being observed (e.g., people being observed may behave in atypical ways).

3.Investigator effects (e.g., personal biases and selective perception of observers)

4.Observer may “go native” (i.e., over-identifying with the group being studied).

5.Sampling of observed people and settings may be limited.

6.Cannot observe large or dispersed populations.

7.Some settings and content of interest cannot be observed.

8.Collection of unimportant material may be moderately high.

9.More expensive to conduct than questionnaires and tests.

10.Data analysis can be time consuming

QUESTIONNAIRES

•A questionnaire is a self-report data collection instrument that is filled out by research participants.

15 principles of questionnaire construction

Principle 1: Make sure the questionnaire items match your research objectives.

Principle 2: Understand your research participants.

•Your participants (not you!) will be filling out the questionnaire.

•Consider the demographic and cultural characteristics of your potential participants so that you can make it understandable to them.

Principle 3: Use natural and familiar language.

•Familiar language is comforting; jargon is not.

Principle 4: Write items that are clear, precise, and relatively short.

•If your participants don't understand the items, your data will be invalid (i.e., your research study will have the garbage in, garbage out, GIGO, syndrome).

•Short items are more easily understood and less stressful than long items.

Principle 5: Do not use "leading" or "loaded" questions.

•Leading questions lead the participant to where you want him or her to be.

•Loaded questions include loaded words (i.e., words that create an emotional reaction or response by your participants).

•Always remember that you do not want the participant's response to be the result of how you worded the question. Always use neutral wording.

Principle 6: Avoid double-barreled questions.

•A double-barreled question combines two or more issues in a single question (e.g., here is a double barreled question: “Do you elicit information from parents and other teachers?” It’s double barreled because if someone answered it, you would not know whether they were referring to parents or teachers or both).

•Does the question include the word "and"? If yes, it might be a double-barreled question.

•Answers to double-barreled questions are ambiguous because two or more ideas are confounded.

Principle 7: Avoid double negatives.

•Does the answer provided by the participant require combining two negatives? (e.g., "I disagree that teachers should not be required to supervise their students during library time"). If yes, rewrite it.

Principle 8: Determine whether an open-ended or a closed ended question is needed.

•Open-ended questions provide qualitative data in the participants' own words. Here is an open ended question: How can your principal improve the morale at your school?

•Closed-ended questions provide quantitative data based on the researcher's response categories.

Principle 9: Use mutually exclusive and exhaustive response categories for closed-ended questions.

•Mutually exclusive categories do not overlap (e.g., ages 0 -10, 10-20, 20-30 are NOT mutually exclusive and should be rewritten as less than 10, 10-19, 20-29, 30-39, .

•Exhaustive categories include all possible responses (e.g., if you are doing a national survey of adult citizens (i.e., 18 or older) then the these categories (18-19, 20-29, 30-39, 40-49, 50-59, 60-69) are NOT exhaustive because there is no where to put someone who is 70 years old or older.

Principle 10: Consider the different types of response categories available for closed-ended questionnaire items.

•Rating scales are the most commonly used, including:

•Numerical rating scales (where the endpoints are anchored; sometimes the center point or area is also labeled).

•1 2 3 4 5 6 7

•Very Low Very High

Fully anchored rating scales (where all the points on the scale are anchored).

1 2 3 4 5

•Strongly Agree Neutral Disagree Strongly

•Agree Disagree

Principle 11: Use multiple items to measure abstract constructs.

•This is required if you want your measures to have high reliability and validity.

Principle 12: Consider using multiple methods when measuring abstract constructs.

•The idea here is that if you only use one method of measurement, then your measurement may be an artifact of that method of measurement.

Principle 13: Use caution if you reverse the wording in some of the items to prevent response sets. (A response set is the tendency of a participant to respond in a specific direction to items regardless of the item content.)

•Reversing the wording of some items can help ensure that participants don't just "speed through" the instrument, checking "yes" or "strongly agree" for all the items.

Principle 14: Develop a questionnaire that is easy for the participant to use.

•The participant must not get confused or lost anywhere in the questionnaire.

•Make sure that the directions are clear and that any filter questions used are easy to follow.

Principle 15: Always pilot test your questionnaire.

•You will always find some problems that you have overlooked!

•The best pilot tests are with people similar to the ones to be included in your research study.

Strengths of questionnaires

•Good for measuring attitudes and eliciting other content from research participants.

•Inexpensive (especially mail questionnaires and group administered questionnaires).

•Can provide information about participants’ internal meanings and ways of thinking.

•Can administer to probability samples.

•Quick turnaround.

•Can be administered to groups.

•Perceived anonymity by respondent may be high.

•Moderately high measurement validity (i.e., high reliability and validity) for well constructed and validated questionnaires.

Weaknesses of questionnaires

•Usually must be kept short.

•Reactive effects may occur (e.g., interviewees may try to show only what is socially desirable).

•Nonresponsive to selective items.

•People filling out questionnaires may not recall important information and may lack self-awareness.

•Response rate may be low for mail and email questionnaires.

•Open-ended items may reflect differences in verbal ability, obscuring the issues of interest.

•Data analysis can be time consuming for open-ended items.

•Measures need validation.

CONDUCTING A PRE-TEST OR PILOT STUDY

•A pilot study may be defined as ‘a small version of a proposed study conducted to refine the methodology.

•It is developed and conducted in a manner similar to the proposed study, using similar research respondents and the same setting.

•A pilot study may also be defined as ‘the process of carrying out a preliminary study going through the entire research procedure with a small sample’.

A pre-test usually refers to a small scale trial of a particular research component.

purposes of a pre-test or pilot study:

1)To determine whether the proposed study is feasible

2)Identify any problems with the research design

3)To ensure that items in the data collection instrument are stated clearly and have the same meaning to all research respondents

4)To assess the time taken to administer the research instrument

5)Determine whether the sample is representative of the population

6)To determine the effectiveness of the sampling technique used

7)Give the researcher the real experience in the field

8)Determine the human and financial resources requirement for the study

9)Determine the effectiveness of the training given to research assistants where necessary

10)Evaluate the procedure for data processing and analysis

•The advantages of conducting the pre-test before you finalize your proposal is that you can draft the work plan and budget based on realistic estimates as well as revise the data collection tools before you submit your proposal for approval.

ETHICAL CONSIDERATIONS IN RESEARCH

Ethics: is defined as that branch of philosophy which deals with one’s conduct and serves as a guide to one’s behaviour’. It is important to note that most professions, including nursing, have a code of conduct to which all members of the profession have to adhere.

Plooy (2003:118) describes ethics in research as ‘that which is morally justifiable’.

Research ethics fundamentally consist of collecting, analyzing and interpreting data in a way that respects the rights of your participants and respondents.

Basic Ethical Principles Underlining the Protection of Human Rights

1.Principle of Respect for Persons It involves two main convictions:

a)Individuals are autonomous, that is, they have the right to self-determination and this right should be respected. This means the research respondents have the right to:

a)Accept or decline to participate in the study without punishment or prejudice

b)Withdraw from the study at any stage

c)Withhold information

d)Seek clarification concerning the purpose of the study

•Individuals with diminished autonomy require protection. This group includes children, the mentally impaired, unconscious patients and institutionalized persons.

•For this group of persons, you will need to seek the consent of their legal guardian.

2. Principle of Justice

This includes the subjects’ right to fair selection and treatment and their right to privacy:

•Right to Privacy: This is the freedom of an individual to determine the time, extent and the circumstances under which private information will be shared with or withheld from others. The privacy of the subject is considered to be protected if the subject is informed and consents to participate in a study and voluntarily shares private information with a researcher.

•Right to Anonymity and Confidentiality:

Complete anonymity exists when the respondents’ identity is not revealed and the information collected is not linked to the respondent.

Confidentiality refers to the researcher’s responsibility to protect all data gathered within the scope of the project from being divulged or made available to any other person, which means the research data should never be shared with outsiders.

A breach of confidentiality can occur when a researcher allows an unauthorized person(s) to gain access to the raw data of a study or when the researcher accidentally reveals the identity of the research respondents.

3. Principle of Beneficence

This principle involves an effort to secure the well being of persons.

It is the right to protect respondents from discomfort and harm. This principle states that one should do what is good and above all should do no harm.

Discomfort and harm can be physical, emotional, spiritual, economic, social or legal.

The Major Content of an Informed Consent

Informed consent revolves around the following three major elements:

–The type of information you need to obtain from the research subjects.

–The degree of understanding required of the subject in order to give consent.

–The fact that the subject has a free choice in giving consent.

Informed consent should be based on the following factors:

–The purpose of the research study

–Foreseen risks

–A guarantee of anonymity and confidentiality

–Identification of the researcher

–Number of subjects involved

–Benefits and compensation or lack of them

Access to Research Population

•Prior to commencing the study, a formal application to the government of Kenya for permission to conduct the research must be written.

•This should include two or more copies of the research proposal, accompanied by a recommendation letter from the supervisor(s) as required by the Kenyan authorities.

•If your institution is authorized to conduct research, there may be a ‘Research and Ethics Committee’. Such a committee is usually vested with the authority of granting research permits, which you could use.

•As a requirement, each research respondent should be requested to accept in writing and sign or affix a thumb print.

•In cases where a respondent can neither read nor write, a consent form should be completed and duly signed after you have clearly explained the purpose of the research.

•You should inform the respondents that their participation is absolutely voluntary and they may pull out of the study whenever they so wish.

•As part of the contract, you should guarantee the respondents absolute confidentiality during and after the study.

Sources of data bias

1.The subject being studied changes their behaviour as a consequence of the research.

2.The researcher may use non-standard measuring scales, imprecise or no guidelines for interviewing.

3.Researchers themselves vary in what they observe or measure, that is, observer variability. E.g., researchers may be selective in their observations, that is, observer bias and measure, question, or note down answers with varying accuracy or follow different interview approaches, with one researcher being more open, friendly and probing than the other.

–Not showing agreement, disagreement or surprise.

–Recording answers precisely as they are provided, without sifting through them or interpreting them.

Data Handling guidelines

–Check that the data gathered is complete and accurate.

–At some stage questionnaires will have to be numbered. Decide if this should be done at the time of the interview or when the questionnaires are stored.

–Identify the person responsible for storing data and the place where it will be stored.

–Decide how data should be stored. Record forms should be kept in the sequence in which they have been numbered.

DATA ENTRY

•Decide on a format, that is, the way you will organize the data in a file.

•Next, design a code, that is, the rules by which the respondents’ answers will be assigned values that can be processed by the computer.

•Then do the actual coding, that is, turn the responses into the standard categories you developed in your coding system.

•Data entry is the next step, which is keying the data into the computer so that you can process it.

•Finally, data cleaning is the final check you make on the data file for accuracy, completeness, and consistency prior to the onset of analysis.

This is because qualitative research uses words while quantitative uses numbers (numerical).

However, the principles are the same for both types. In both cases the researcher has to do the following:

a)Describe the sample population by providing a description of the:

–Respondents, for instance, key informants or focus group members.

–Age, sex, occupation, educational background etc.

b)Order, reduce and/or code the data (data processing).

c)Display the summaries of data for interpretation.

d)Draw conclusions.

e)Develop strategies for testing or confirming the findings to prove their validity.

Measures of Central Tendency

•Referred to as 'average' measures. They describe how closely related the data is.

1.Mode: it is the numerical value or score that occurs most times. It is the most suitable measure of central tendency for nominal data.

2.Median: it is the score at the exact centre of a distribution; it is also called the 50th percentile. It is the most central value when raw data is arranged on a scale from the highest to the lowest.

3.Mean: It is the total sum of scores divided by the number of scores being summed. The mean is the most suitable measure of central tendency for interval and ratio level data.

Measures of Dispersion

•Are used to measure the individual differences of scores in a sample. They give an indication of how scores in a sample are dispersed around the mean.

•They show how different the scores are or the extents to which individual scores deviate from one another.

•If the individual scores are similar, the measure of variability is small and the sample is relatively similar or homogeneous in terms of those scores. A wide variation in scores may indicate a heterogeneous sample.

1.Range: It is obtained by subtracting the lowest score from the highest score. The range is the difference between the highest and lowest score. It is not a very significant statistical measure.

2.Variance: it is a measure of how individual scores in a set of data vary in their distribution from one to the other.

3.Standard Deviation: It is calculated by finding the square root of variance - that means you have to calculate the variance first.

MEASUREMENT SCALES

1.Nominal scale: the lowest level of measurement. It groups subjects or cases from the sample into categories. Variables which can only be measured at the nominal scale include: sex, race, marital status, color etc

2.Ordinal scale: it not only groups subjects into categories, but it also ranks them into some order, this could be in an increasing order. i.e., in an ordinal scale, numerals are used to represent relative position or order among the values of the variables. E.g.; social class, military rank etc.

3.Interval scale: The numerals are assigned to each measure and ranked in an order and the intervals between the numerals are equal.

Mathematical operations are limited to additions and deductions; multiplication and division are not applicable.

An interval scale does not have a true zero point. The minimum and maximum points o the scale are only arbitrary

4.Ratio scale: is the highest level of measurement. It is the most precise method of measuring variables. It has all the characteristics of the other scales. The only additional characteristic is that it has a true zero point and all the mathematical operations can be applied to yield meaningful values. Most physical objects can be measured at the ratio scale. E.g. height, weight, distance, age, area,

Qualitative Data Presentation and Analysis

1.Organizing the Data: involves putting all the information in a simple format that can be understood. This is known as ‘cleaning’ the data.

2.Creating Categories, Themes and Patterns: The researcher needs to be very familiar with the data so as to establish relationships among these categories. One use the research questions or discussion topics.

3.Analyzing and Interpreting the Data: it involves evaluating the data to determine its usefulness

and accuracy.

4.Writing the Report: Unlike the quantitative research where the report writing is done after analyzing the data, in qualitative research techniques, the writing and the analysis go hand in hand.

Quantitative Data Presentation and Analysis

1.Tabular Method

–Simple Table: usually a single line of characters explaining a few columns of information.

–Compound Table: a single line of characters has been described by two or more components of information.

When constructing tables it is important that:

–You give correct consecutive numbers to the tables and indicate the title of the table at the top.

–Clearly indicate the totals and percentages.

–Show where the data is obtained from, that is the source of the data with the year when the data was collected clearly shown.

2. Graphic Method

Graphs are used to organize and describe data.

This enables the reader to see at a glance the trend of distribution of the data. Graphs have two axes: vertical and horizontal.

Scores are usually presented along the horizontal axis, while the frequency is placed along the vertical axis.

It is important to note that the intersection point between the vertical and horizontal axes is usually represented by a zero (0).

Graphs should be well labelled both along the vertical axis and the horizontal. There are three common graphic methods that you may use for presenting data, i.e. Bar Charts, histograms, frequency polygons

•Bar Charts: used when the data being presented is discrete or when the scale is nominal. Bar charts are quite similar to histograms with the exception that there are spaces in bar charts.

•Histograms: Unlike the bar chart, in the histogram there are no spaces between the bars. A histogram in many cases is used to represent continuous variables.

•Frequency Polygons

Frequency polygons are drawn based on the frequencies of the observations along the vertical axis against the group or class midpoints.

They form a polygon shape hence the name.

3.Charts Method: they include; pie charts, doughnut charts, and scatter charts. One of the commonest types of charts used is the pie chart. Pie charts are relatively easy to interpret.

Each portion represents a variable.

Study limitations Limitations may include:

1.Factors such as the inherent weakness in the sampling method, faulty designs and controls, weaknesses in the methods used to collect data and so on.

2.Time factor due to pressure of work.

3.Expenses involved if grant is not secured.

4.Possibility that some of the respondents may not agree to participate in the study.

5.Diverse spread of the target population, which may hinder easy access to respondents.

The researcher has the opportunity to recommend ways to minimize or eliminate the limitations of the current study or to offer alternative methodology or improvements of the methods of the study presented.

REFERENCES, CITATIONS AND BIBLIOGRAPHY

DESCRIPTION:

•A reference or citation is a description of any document from which you have taken information, e.g. a complete book, a chapter from it, a journal article, a newspaper article, a web page, or DVD etc

•Harvard referencing style is the mostly used.

What is “Citing”?

“Citing” a reference is the act of recording it. It is made in two places:

1.a brief entry for each source in the text of your work, which then leads your reader to …

2.your source, in full, at the end of your work, as an alphabetical reference list.

As the list is in alphabetical order, it is easy to pick out the required author's work.

IMPORTANCE OF CITATION &

REFERENCING

•It is both a legal requirement and academic practice to provide references to guide your reader to the sources you have used

•To support the arguments you are making

•To demonstrate the breadth of your research,

•To credit the established work of others.

NOTE:

•Failure to acknowledge your sources is likely to lead to a suspicion of plagiarism – i.e. trying to pass off someone else's work as your own: it is a form of cheating.

•Incomplete or inaccurate referencing also reflects badly on your work

How it works

•There are 2 parts:

1.Author + Date in your text.

2.Full reference in the Reference List

•Whoever you cite in your text has to match your reference list as the list is in alphabetical order, normally by author. It must be in alphabetical order

•e.g. In your text: …Marieb and Hoehn (2007)… leads to the

reference list and finds: Marieb, E. N. and Hoehn, K. (2007) Human anatomy and physiology. 7th International ed. San Francisco: Benjamin Cummings.

SECONDARY REFERENCING

• If you refer to a document which you DID NOT read, but which was cited (referenced) by somebody else whose work you DID read, you must make this clear. When you compile your reference list you must only cite the work in which you read it. Try to avoid this type of reference as you cannot always check the original and are relying on interpretation by others.

Examples:

•Dunn (1988), as cited by Campbell and Muncer (1998), believed that …

or Dunn (1988) revealed that ….. (cited in Campbell and

Muncer, 1998, p.226)

NB: your reference list will include the full details of the Campbell and Muncer work, but no mention of Dunn‟s.

How to Put References into the Text of

your Essay / Report

Author/s and Date

qFor each reference you make in the text of your essay, you need to provide:

•The authority: usually surname (family name) of the author(s), maybe a corporate author

•The date it was published.

Example: (Nursing and Midwifery Council, 2008)

qIf you include the author‟s name as part of the sentence statement, only the date needs to be in brackets.

•Example: … Hartley (1999) declared that …

qIf it is not part of your sentence, both the name and date must be in brackets, separated by a comma.

•Example: … although other authors have denied this (Hartley, 1999).

qThe page number(s) must be added if a specific part needs to be identified or a direct quote made.

•Example: …which is described there in detail (Hartley, 1999 p.172).

qIf there are two authors:

•Example: In the much acclaimed work on the subject by Martin and Frost (2001), it is clear …

•For three authors or more, it is usual to use the Latin et al (meaning “and others”) after the name of the first author.

•Example: … Anderson et al (2003) concluded that …

Multiple references to the same author

•If you cite different documents by the same author which were published in the same year, to distinguish between them add the letters a, b, c, etc. in lower case after the year. Repeat in the reference list.

•Example: … (Williamson, 2001a), (Williamson, 2001b) etc.

…

Quotations in the Text

•If you quote the exact words directly from a text you must use quotation marks to indicate this.

•The author(s) and date must be stated, and if possible the page number (or at least the chapter heading e.g. Chapter 6) from which the quote is taken.

NB: Page numbers for books are not included in the Reference List

•Example: … Jackson (2004, p.575) declared that “This is the finest example of postmodernism …”

•If page numbers are in separate sequences and therefore duplicated e.g. different issues of a journal throughout the year, or sections of a book, you must include the issue or section number or name.

Listing Your References at the End of

Your Work

NOTE: Your list should have both printed and electronic sources in one single alphabetical sequence.

Order of referencing textbooks

•Surname of author(s), comma, initial(s), full stop

•Year of publication (in brackets)

•The title (in italics with only the first letter of first word capitalized), colon between short and secondary/sub title, full stop.

•The edition (if other than the first), full stop

•Place of publication (the first city or town) followed by a colon

•Publisher’s name, full stop

Example:

•Macionis, J. J. and Plummer, J. (2008) Sociology: a global

introduction. 4th ed. Harlow: Pearson, Prentice Hall.

E-books (Electronic Books)

As above examples, except for certain additions. You need to include:

•Author (or editor) surname and initials

•Year (in brackets). Always use the publication date of the version being used.

•Title of book (and any subtitle) - italics or underlined. Only initial letter capitalized.

•Edition (other than the first)

•Place of publication (of printed original - if available) followed by a colon(:)

•Publisher's name.

•Available from: (i.e. the e-book service you used), URL (web address)

•(Date accessed).

Example:

•White, R. and Downs, T. E. (2005) How computers work, 8th ed. Indianapolis: Que. [Online]. Available from: Safari Tech Books Online. http://0-proquest.safaribooksonline.com [Accessed: 16 August 2007].

JOURNAL ARTICLES

qFor journals, details are normally on the contents page and usually at the top or bottom of every page of each article. You need to include:

•Surname of the author(s), comma, initial(s), full stop

•Year of publication in brackets

•Title of the ARTICLE ( only first word with capitalized initial letter, unless proper name), comma

•Title of the JOURNAL (in italics), comma

•Volume number, issue or part number (in brackets), comma

•First and last pages of the article separated by a hyphen and indicated by the abbreviation “pp.”

EXAMPLE

•Smith, A. and Jack, K. (2005) Reflective practice: a meaningful task for students, Nursing Standard, 19 (26), pp. 33-37.

•Morrison, C. and Jutting, J. (2005) Women’s discrimination in developing countries: a new data set for better policies, World Development. July, 33 (7), pp. 1065-1081. [Online]. Available from: Science Direct. http://sciencedirect.com [Accessed 31 July 2005].

Papers presented at a conference

Mugenda, O. (1999) Redefining and Actualizing the Research Mission in African Universities. Paper presented at the BOLESWA Educational Research Symposium, Maseru, Lesotho, July, (1999).

Newspaper article:

Ngw’eno, H.B. (1993, September). Multiply and fill the earth. The Weekly Review,pp 15 – 17.

Introduction to Biostatistics

•What is statistics?

üStatistics is the summary of information (data) in a meaningful fashion, and its appropriate presentation.

üStatistics is the postulation of a plausible model explaining the mechanism that generates the data, with the ultimate goal to extrapolate and predict data under circumstances beyond the current experiment

•Bio-statistics is the segment of statistics that deals with data arising from biological processes or medical experiments

•Two broad branches in statistics

1. Descriptive statistics

Once data has been collected, normally the step that follows is to summarize the data, if possible, with one or two summary statistics. Summary or descriptive statistics describe the original data set (the set of responses for each question) by using just one or two numbers – typically an average and a measure of dispersion.

2. Inferential Statistics

This is the branch of statistics that makes use of sample data to make generalization concerning the population parameters. Here theoretical distributions become handy.

Errors in statistical inference

•Type I error (or, error of the first kind) and

•Type II error (or, error of the second kind)

Are precise technical terms used in statistics to describe particular flaws in a testing process, where a true null hypothesis was incorrectly rejected (Type I error) or where one fails to reject a false null hypothesis (Type II error).

TYPE 1 ERROR

•Occurs when the null hypothesis (H0) is true, but is rejected. It is asserting something that is absent, a false hit.

•A type I error may be compared with a so called false positive (a result that indicates that a given condition is present when it actually is not present) in tests where a single condition is tested for.

•A Type I error is committed when we fail to believe a truth. In terms of folk tales, an investigator may be "crying wolf" without a wolf in sight (raising a false alarm) (H0: no wolf).

TYPE 2 ERROR

•Occurs when the null hypothesis is false, but it is erroneously accepted as true. It is missing to see what is present, a miss.

•A type II error may be compared with a so-called false negative (where an actual 'hit' was disregarded by the test and seen as a 'miss') in a test checking for a single condition with a definitive result of true or false.

•A Type II error occurs when we believe a falsehood. In terms of folk tales, an investigator may fail to see the wolf ("failing to raise an alarm“).

RELIABILITY AND VALIDITY IN RESEARCH

Reliability

•Def: is the extent to which an experiment, test, or any measuring procedure yields the same result on repeated trials.

•Without the agreement of independent observers able to replicate research procedures, or the ability to use research tools and procedures that yield consistent measurements, researchers would be unable to satisfactorily draw conclusions, formulate theories, or make claims about the generalizability of their research.

Types of reliability are:

•Equivalency Reliability

•Stability Reliability

•Internal Consistency

•Interrater Reliability

Validity

•Validity refers to the degree to which a study accurately reflects or assesses the specific concept that the researcher is attempting to measure.

•While reliability is concerned with the accuracy of the actual measuring instrument or procedure, validity is concerned with the study's success at measuring what the researchers set out to measure.

•Validity is both external and internal.

•External validity refers to the extent to which the results of a study are generalizable or transferable.

•Internal validity refers to

–(1) the rigor with which the study was conducted (e.g., the study's design, the care taken to conduct measurements, and decisions concerning what was and wasn't measured) and

–(2) the extent to which the designers of a study have taken into account alternative explanations for any causal relationships they explore