BUSINESS RESEARCH MODULE - PRESENTATION

by

Prof. Philip AE Serumaga-Zake

UNISA SBL

22 March 2010

ROLE OF RESEARCH IN THE MBL PROGRAMME

The module MBL925R prepares you for the research project that you have to complete during your final year.

The importance of this individual research project is highlighted by the fact that it contributes 60% towards your final year’s marks.

ROLE OF RESEARCH IN THE BUSINESS ENVIRONMENTTHIS MO

This module (MBL925-R) prepares you to both conduct and critically evaluate business or market research in your working environment.

• Zikmund, et al. (2000) defines business research as the application of the scientific method in searching the truth about business phenomena. These activities include defining business opportunities and problems, generating and evaluating alternative courses of action, and monitoring employee and organizational performance.

•Business research helps to provide managers with the knowledge regarding their organizations, the market, the economy or any other area of uncertainty,

THE CONCEPT OF SCIENTIFIC RESEARCH: KEY COMPONENTS OF THE RESEARCH PROCESS

Purpose of science concerns expansion of knowledge and search for building theories. Research can be defined as: •A systematic inquiry that provides information for solving a problem. •A methodology in an attempt to describe, explain and change (improve) human behaviour. •A formal, systematic application of the scientific method to the problem.  The research process is built on three key features, namely: • Clearly stated research questions/objectives to be addressed • A research context for the questions and a rationale for why it is important that these questions should be answered or explored • Research methods for addressing and answering the research questions. • Purpose of science concerns expansion of knowledge and search for building theories.

•Research starts by the selection of a topic, a ‘domain phenomenon’ to be studied. •You may for e.g., be curious about an interesting phenomenon, a problem or a concern to be addressed; to test some existing theory or to generate new models or hypothesis. Steps of the scientific method: •Start from general questions or problems •Narrow down to focus on one specific aspect. A research report generally begins with an overview of the previous research and real-world observations, the researcher then states how this led to defining a research problem. •Design a research study •Collect data •Analyze this aspect •Finally conclude, and •Generalize to the real world.

FORMULATING A PROBLEM STATEMENT/RESEARCH QUESTION

Choosing a topic•Research starts by the selection of a topic, a ‘domain phenomenon’ to be studied. •You may for e.g., •be curious about an interesting phenomenon•a problem to be solved or a concern to be addressed•you may want to test some existing theory or you may want to generate new models or hypothesis, for e.g., to come up with new ideas.Some points about topics for research: •Topics should not have yes/no answers. •Topics should not have obvious answers. •When choosing a topic, it should not matter to you what you find out – you must be unbiased and not expect a particular finding – you may be wrong and will need to explain your results.

•Your topic should be do‐able in the time available, so the scope needs to be carefully defined – not too big and not too small. •The title should preferably not be more than 16 words. •Your topic should add at least some value / new knowledge to what is already known. •Your topic should have a basis in business or management. •Your topic should be something you can get excited about, or at least are interested in. Note: The research should be related to leadership, business or management science

Sources of research topics include:•Existing Research Reports –e.g. Recommendations for future research. •Application of an existing theory in a different setting or a different context. •An investigation into whether a particular early theory regarding say, strategy, leadership, customer relations, diversity management, the financial markets, globalisation, economic theory etc still applies today. •Exploration of a gap or contradiction in existing theory / research. •An exploration of factors affecting a certain situation, e.g. identification of the factors promoting the success of small businesses in Gauteng. •Investigating a business problem or issue •Any contemporary or emerging issue in your area of interest, e.g. as reported in journals. •Ask an academic or lecturer in your area of interest about topics he/she is researching and perhaps take a portion of that. •Ask your business colleagues, your manager or someone senior in your organisation, your customers, suppliers or other stakeholders for ideas or issues/problems being experienced .

Formulating or Defining the Research Problem •Researchers organize their research by formulating and defining a research problem. •This helps them focus the research process so that they can draw conclusions reflecting the real world in the best possible way. •The target population should be defined beforehand. Dfn: The totality of the units studied is the target population.•The research problem is the foundation of the research and specific objectives drive the scientific process. A research question can be regarded as a statement of an intellectual puzzle.

Questions:•What exactly do you want to study? •What do you want to know? •Why is it worth studying? •Significance? For e.g., does it contribute to the body of knowledge?

•According to Black (1993), research questions sometimes are "too vague and do not provide sufficient direction for the research effort". •One can attempt to evaluate the quality of a research question by considering three points (Kerlinger, 1986):•the research question expresses a relationship between variables•the question is stated in an unambiguous form and•the question might be tested empiricallyThe problem statement seeks to give a more precise description of the domain phenomenon to be researched on. Research problems are usually expressed in terms of questions.E.g.: What is the problem? What happened? Or Why does/did it happen?

There are two popular ways of stating a research problem: as a question and as a hypothesis. •A hypothesis is a statement you believe is true. •Alternatively, a hypothesis represents a probable answer to the research question, but the probability that the answer is correct would still need to be tested through further investigation. •It may be favoured over the question when there is a good reason to believe that a proposed solution to the research issue is correct, but that belief still needs to be corroborated or refuted by evidence or when you intend to apply a statistical test to the data you collect, casting the problem as a hypothesis renders statistical testing more convenient.

•The vast majority of problems are expressed as questions that involve who, how, which, why, what, when, where, how much, how frequently, or several of these.

Examples are:•How do supermarkets set their selling prices for produce and, in particular, how much does the spoilage of produce affect pricing?

•Which method of teaching (beginning reading) best equips first-graders to infer the meanings of new words?

•What characteristics are most significant in differentiating people of the upper-class from those of the lower-class in Johannesburg?

•When (during the day, month, and year) do people most frequently suffer feelings of depression, and why at those times?

Marx's sources of research questions Intellectual puzzles and contradictions•The existing literature •Replication •Structures and functions •Opposition •Social problems •The counter-intuitive •Deviant cases and atypical events •New methods and theories •Social and technical developments and trends •Personal experience •Sponsors and teachers Having selected your research topic and questions, the next stage is to begin designing and planning your research project, the focus of which is usually expressed in terms of aims and objectives.

Research design•A master plan that specifies the methods and procedures for collecting and analyzing the needed information.•A framework or plan of action for the research.

It includes:•Objectives•Sources of information•The design technique (a survey or experiment)•Sampling methodology•The schedule and•Costs of the research

Empirical EvidenceThe empirical evidence is evidence which serves the purpose of testing a hypothesis or theory. Field Experiments (Quasi-experiment)•A field study is an experiment performed in the 'real' world. •Unlike case studies and observational studies, a field experiment still follows all of the steps of the scientific process.•Pilot studies are often used to test the feasibility of an extensive research program.

Observational studyThis type of research draws a conclusion by comparing subjects against a control group.

Example 3A research study comparing the risk of developing lung cancer, between smokers and non-smokers. •The main problem: The researcher has no control over the composition of the control groups, and cannot randomize the allocation of subjects. •This can create bias, and can also mask cause and effect relationships or, alternatively, suggest correlations where there are none.

•Randomization is assumed to even out external causal effects, but this is impossible in an observational study.

Unit of analysisIt is the entity, who or whom is being analysed. E.g. individual people, groups, organizations, etc.•Data are facts or recorded measures of certain phenomena (things or events).•Information is processed or summarized data to support decision making or define the relationship between two facts.

IDENTIFYING THE CONCEPTS TO BE MEASURED AND/OR OBSERVED THAT WILL ENABLE THEM TO ANSWER A RESEARCH QUESTION - OPERATIONALISATION

•A concept or construct is a generalized idea about a class of objects, attributes, occurrences or processes that has been given a name (Zikmund, et al., 2000). •Operationalization is then used to give some indication of the exact definitions of the variables, and the type of scientific measurements to be used. •Literature review also helps with the test to be used, or the methodology, and helps the researcher to refine the research process. •Operationalization is to take a concept, such as 'helping behavior', and try to measure it by specific observations, e.g. how likely are people to help a stranger with problems. •Operationalization is the process of strictly defining variables into measurable factors. •The process defines fuzzy concepts and allows them to be measured, empirically and quantitatively. Operationalization sets down exact definitions of each variable, increasing the quality of the results, and improving the robustness of the design. •It determines how the researchers are going to measure an emotion or concept, such as the level of distress or aggression.

OPERATIONALIZATIONOperationalization is to take a concept, such as 'helping behavior', and try to measure it by specific observations, e.g. how likely are people to help a stranger with problems. •Operationalization is the process of strictly defining variables into measurable factors.•The process defines fuzzy concepts and allows them to be measured, empirically and quantitatively. Operationalization sets down exact definitions of each variable, increasing the quality of the results, and improving the robustness of the design.•It determines how the researchers are going to measure an emotion or concept, such as the level of distress or aggression.

The Operational Definitions•The operational definition is the determining of the scalar properties of the variables. •If a researcher is measuring abstract concepts, such as intelligence, emotions, and subjective responses, then a system of measuring numerically needs to be established, allowing statistical analysis and replication.

For e.g., Human responses could be measured with a questionnaire from ‘1- strongly disagree’, to ‘5 – strongly agree’.•These measurements are always subjective, but statistics can be used in analysis.•Such measurements are arbitrary, but allow others to replicate the research.

Fuzzy concepts•Fuzzy concepts are vague ideas, concepts that lack clarity or are only partially true. •It is important to define the variables to facilitate accurate replication of the research process.

Example 5A scientist might propose the hypothesis:“Children grow quicker if they eat vegetables.”

What does the statement mean by ‘children’? •Are they from America or Africa? •What age are they? Are the children boys or girls?•There are billions of children in the world, so how do you define the sample groups?

How is ‘growth’ defined? •Is it weight, height, mental growth or strength? The statement does not strictly define the measurable, dependent variable.

What does the term ‘quicker’ mean? •What units, and what timescale, will be used to measure this? •A short-term experiment, lasting one month, may give wildly different results than a longer-term study.

•The frequency of sampling is important for operationalization, too. •If you were conducting the experiment over one year, it would not be practical to test the weight every 5 minutes, or even every month. •The first is impractical, and the latter will not generate enough analyzable data points.

What are ‘vegetables’? •There are hundreds of different types of vegetable, each containing different levels of vitamins and minerals.

•Are the children fed raw vegetables, or are they cooked? •How does the researcher standardize diets, and ensure that the children eat their greens?

The above hypothesis is not a bad statement, but it needs clarifying and strengthening, a process called operationalization.

•The researcher could narrow down the range of children, by specifying age, sex, nationality, or a combination of attributes. •As long as the sample group is representative of the wider group, then the statement is more clearly defined.•Growth may be defined as height or weight. •The researcher must select a definable and measurable variable, which will form part of the research problem and hypothesis.

•Quicker would be redefined as a period of time, and stipulate the frequency of sampling. •The initial research design could specify three months or one year, giving a reasonable time scale and taking into account time and budget restraints.•Each sample group could be fed the same diet, or different combinations of vegetables. •The researcher might decide that the hypothesis could revolve around vitamin C intake, so the vegetables could be analyzed for the average vitamin content.•Alternatively, a researcher might decide to use an ordinal scale of measurement, asking subjects to fill in a questionnaire about their dietary habits.In this way, the fuzzy concept has undergone a period of operationalization, and the hypothesis takes on a testable format.

CHOOSING AN APPROPRIATE RESEARCH METHODOLOGY: QUANTITATIVE APPROACH VERSUS QUALITATIVE APPROACH:

Which Research Method to choose?

What design you choose depends on different factors. •What information do you want? •Feasibility •How reliable should the information be? •Is it ethical to conduct the study? •The cost of the design

•The selection of the research method is crucial for what conclusions you can make about a phenomenon.•It affects what you can say about the cause and factors influencing the phenomenon.•It is also important to choose a research method which is within the limits of what the researcher can do. •Time, money, feasibility, ethics and availability to measure the phenomenon correctly are examples of issues constraining the research.

•Qualitative researchers aim to gather an in-depth understanding of human behavior and the reasons that govern such behavior. •In qualitative research; •Smaller but focused samples are more often needed, rather than large random samples. •Purposive sampling is normally used to have key informants in the sample. •Data analysis use nonstatistical methods and approaches to analysis are holistic and contextual. •In quantitative research, statistical methods are used to test hypotheses.

Examples 4•Some methods are better suited to the study of certain questions than others. •Some methods might be clearly inappropriate to your research question.

Example iConsider for example the case of a researcher interested in studying the influence of Nazism and neo-Nazism on racial attacks in the UK. •This research problem might be studied by sending a questionnaire or doing interviews to researchers and historians of Nazism on the roots of neo-Nazism.•This would be an empirical approach to the research problem/question. •Alternatively one could read and analyse the writings of historians and come-up with some new or innovative interpretation on the roots of neo-Nazism.•This would not be an empirically-based approach because one is not generating data, one is analysing and studying data produced by others and based on that data one produces a theory or a model.

These methods will allow us to trace the influence of Nazism on neo-Nazism but they will not allow us to investigate the second part of the question i.e. racial attacks in the U.K.

•Field research through either participant or non-participant observation might be a more appropriate method to answer this angle of the research question.

Example iiLet us assume that you are interested in studying the effect of prolonged exposure in battle-trenches on the health of survivors of battles during WWI. •Although in theory you could study this research question by interviewing survivors, in practical terms this method is hardly possible because most survivors are now too old to remember, or most survivors of particular battles are now dead. •If you had studied that question 50 years ago, you could have in fact interviewed people, now however, that method is hardly appropriate. •An alternative method to interviews in this particular case would be the analysis of other sources of data, like diaries of survivors, letters of survivors, letters and records of medical personnel that treated wounded soldiers etc.

Something that must be realized when choosing a research method is that your chosen method is also your way of generating data.

Ser. No.

Quantitative – Assumptions Qualitative - Assumptions

Creswell1

2

3

4

5

Ontological: a single objective world

Epistemological: independence from variables under study

Axiological: act in a value-free and unbiased manner

Rhetorical: Most often use impersonal, formal and rule-based text

Tends to apply deduction, limited cause-effect relationships and context free methods

Multiple subjectively derived realities can existResearchers must interact with their studied phenomena

Overtly act in a value-laden and biased fashion

Use personalized, informal and context-based language

Tends to apply induction, multivariate and multiprocess interaction and context specific methods

Quantitative Versus Qualitative Research (see Lee)

Cassell and SymonNumbers or quantification – bias towards counting

Often seeks objective (or less biased) and freely calibrated descriptions-Researchers favor a more detached, impersonal orientation to data

More rule driven-Enter with relatively clear mental models to follow-Usually want to anticipate and eliminate problems before they occur, say thru research design

Focus more on predicting outcomes and less on process variables

A more context-free-More generalizable

Less explicit about participants’ reaction

No numbers or interpretation-Endeavor to describe organizational phenomena-Counting only if necessary

Researchers explicitly and overtly apply their own subjective interpretation-Personal investment in the data

Maximally responsive to the constraints imposed by their immediate situation and empirical data-Prefer to have the maximal degree of flexibility

Focus more on understanding organizational processes and less on predicting outcomes

Heavily grounded within local context in which the phenomena of interest occur -Generalization is problematic

More explicit about participants’ reaction-Recognize and integrate the effects of the research process itself into the study’s results

Kvale

Involve more intensive calibration of organizational parts and its analysis include at least equal interval scaling

Better suited to questions of differences in degree within and across these categorical states

Most often focus on the identification of meaningful categories (or parts) of organizational phenomena-Often involve content analysis and nominal or ordinal calibration

Best suited to questions concerning differences in categorical states

Other differences:•Quantitative research is better suited to theory testing and qualitative research is better suited to theory creationNote: there are exceptions. E.g. factor analysis can be used to generate theories

Summary•Qualitative research is often taken to mean inductive, theory generating, subjective and nonpositivist.•Quantitative research is often taken to mean deductive, theory testing, objective and positivist.•Both approaches can be used in a study. E.g. Quantitative study followed by a qualitative study for deeper and richer information.

DATA COLLECTION

•For Qualitative researchers: E.g., Approaches in collecting data: grounded theory, ethnography and phenomenology. •Methods: e.g., Observation, and interviewing and focus group discussion. •Forms of the data collected: interviews and group discussions, observation and reflection field notes, various texts, pictures, and other materials. •Qualitative research often categorizes data into patterns as the primary basis for organizing, interpreting and reporting results. Quantitative research: scientific experiments or surveys to collect primary data or use already collected (and processed) data called secondary data in their studies.

Methods of Data CollectionData CollectionMethods include interviews and focus group discussions, observation (Participant Observation, Non-participant Observation), field notes, various texts, pictures, and other materials, Structured Interview, Unstructured Interview, Analysis of documents and materials.

•Observations (Key, 1997)•In qualitative research, observations are intentionally unstructured and free-flowing.•Very flexible.•Draw backs are:•Observation can be time wasting for a novice researcher – recording even irrelevant information.•The presence of an interviewer may bias the data collected•Written notes are always insufficient to capture the richness of the phenomenon, yet audiotapes and videotapes are not always completely dependable either because their presence may make participants uncomfortable.

Systematically seeks out and organizes data concerning what is being studied based on a social science theory and methodology rather than focusing on achieving a situationally defined goal.

Keeps detailed records of what occurs, including those things characteristically taken for granted.

Periodically detaches self from the situation to review records from the neutral position of a social scientist.

Constantly monitors observations and records for evidence of personal bias or prejudice.

Participant Observation 

The researcher should control his reactions or emotions. The purpose of the interview is to find out what views people hold; their views should be unbiased by evaluative responses on the researcher’s part.

The researcher should choose an interview environment and conditions in which the participants feel comfortable, secure, and at ease enough to speak openly about their point of view.

The researcher should avoid presenting "yes" or "no" questions which tend to stifle detail.

The researcher should be flexible in his or her approach to the informants.

Group interviews can be useful, particularly in initial interviews.

The researcher should consider to what degree the interview questioning is "recursive." As applied to interviewing, what has been said in an interview is used to determine or define further questioning.

•Interviewing

Interview•To ask about events, the interviewer must be aware that participants rely on their memories, which may bring in distortions.•Interviews are either open-ended or semi structured – revolving around a few central questions.•To conduct a focus group, researchers gather several people less that 10 or 12 to discuss a particular issue for 1 or 2 hours.•When conducting a focus group discussion, make sure that no one dominates the discussion and keep people focused.•Focus groups are useful when:•Time is limited•People feel more comfortable talking in a group than alone•Interaction among participants may be more informative than individually conducted interview.•Researcher is having difficult interpreting what he/she observes.When interviewing, both parties, the interviewer and the interviewee must be on equal footing and there must be mutual trust between them.

Structured interviews

•Limited time and financial resources may lead some qualitative researchers to pursue other data collection techniques, such as a structured interview schedule with open-ended questions.

•Drawing on the theoretical and research literature, such questions may be formulated and organized in advance to address a specific research topic.

•Interviewers are expected to take field notes or to keep a field diary of observations made during the interview.

•For focus groups, key informants are interviewed. It involves a moderator to facilitate a small group discussion between selected individuals on a particular topic.

•This is a popular method in market research and testing new initiatives with users/workers.

Quantitative Research Design

Experiments, sometimes referred to as true science) are normally used in studies. They use traditional mathematical and statistical means to measure results conclusively. •They are most commonly used by physical scientists, although social sciences, education and economics have been known to use this type of research. •Quantitative studies use a standard format, with a few minor inter-disciplinary differences, of generating a hypothesis to be proved or disproved. •This hypothesis must be provable by mathematical and statistical means, and is the basis around which the whole experiment is designed.

•Randomization of any study groups is essential, and a control group should be included, wherever possible. •A sound quantitative design should only manipulate one variable at a time, or statistical analysis becomes cumbersome and open to question.•Ideally, the research should be constructed in a manner that allows others to repeat the experiment and obtain similar results.

Advantages•Quantitative research design is an excellent way of finalizing results and proving or disproving a hypothesis. •The structure is standard across many scientific fields and disciplines. •After statistical analysis of the results, a comprehensive answer is reached, and the results can be legitimately discussed and published. •Quantitative studies try to filter out external factors, if properly designed, and so the results gained can be seen as real and unbiased.•Quantitative experiments are useful for testing the results gained by a series of qualitative experiments, leading to a final answer, and a narrowing down of possible directions for follow up research to take.

Disadvantages•Quantitative studies must be carefully planned to ensure that there is complete randomization and correct designation of control groups. •Quantitative studies usually require extensive statistical analysis.

Survey Research DesignA Survey•A survey in which every element of the population is studied is referred to as a census survey. •A survey in which only a sub-set or a few elements of the population (i.e. sample) are used to study the whole population is known as a sample survey.•Every effort should be made to minimize the difference between the sampled population and the target population. •A sample survey is often more accurate and in most cases better than a census for the following reasons:

•Using an interview in an enormous project such as a census survey would require the service of a great number of field workers some of whom may not be well-trained.•Census survey takes much longer•The cost of a census is considerably greater, and supervision, the capturing and processing of data, training require much more effort.

Five preliminary steps that should be taken when embarking on a research project. They are:1.choose a topic2.review the literature3.determine the research question or objectives4.develop a hypothesis, and 5.operationalise, that is, find the suitable research methodology and use it to implement the research plan to answer the research question or to achieve pre-determined objectives of the study. Two additional considerations that are very crucial, namely: 1.designing a representative sample, and 2.a questionnaire to be used to collect data. 3.By a representative sample, we mean an accurate proportional representation of the population under study. 4.In this sample, every characteristic in the population should be well or fairly represented. 5.In other words, to obtain reliable results on the characteristics of interest of the population, a sample, through the process of generalization, should in all relevant respects be a true image or reflection of the population.The survey research design is often used because of the low cost and easy accessible information.

•Before you start the planning, it is important that you consult a statistician about the survey research design. •This helps you to know the right sample size and obtain a representative sample to make it a valid survey and prevent inaccurate results.

Types of surveys•There are two basic types of surveys: cross-sectional surveys and longitudinal surveys. •Cross-sectional surveys are used to gather data on a population at one point in time. •An example of a cross –sectional survey is using a questionnaire to collect data on annual household expenditure in a country at a given time of the year. •Longitudinal surveys gather data over a period of time. •The researcher may then analyse the data to study changes in the population and attempt, for e.g., to explain them. •The three main longitudinal surveys are trend studies, cohort studies and panel studies.

Longitudinal StudyA longitudinal study is observational research performed over a period of years or even decades, and allows social scientists and economists to study long-term effects in a human population. A cohort study is a subset of the longitudinal study because it observes the effect on a specific group of people over time. There are two main sub-types of cohort study, the retrospective and the prospective cohort study. The major difference between the two is that the retrospective looks at phenomena that have already happened, whilst the prospective type starts from the present.

Examples 7Trend studies focus on a particular population, which is sampled and scrutinized repeatedly. E.g. A trend study is an annual survey of the average hourly earnings of workers in the manufacturing industry in South Africa over a long period of time. •A trend line is then fitted to the data. •While samples are of the same population, they are typically not composed of the same people. •Several data from several studies of the same population (not necessarily done by the same researcher) may be combined to investigate the trend of the characteristic (or variable) of interest.

Cohort studies also focus on a particular population sampled and studied more than once. E.g. A sample of the 2010 first-year students at the SBL could be questioned regarding their attitude toward the library staff. •Two years later, the researcher could question another sample of the same 2010 first-year students and study any changes in attitude. Note: If after the two years, the 2012 first-year students were studied, the study would be a trend study instead.

Retrospective Cohort StudyThe retrospective case study is historical in nature. Whilst still beginning with the division into cohorts, the researcher looks at historical data to judge the effects of the variable. •It is a lot easier than the prospective, but there is no control, and confounding variables can be a problem, as the researcher cannot easily assess the lifestyle of the subject.•A retrospective study is a very cheap and effective way of studying health risks or the effects of exposure to pollutants and toxins. •It gives results quickly, at the cost of validity, because it is impossible to eliminate all of the potentially confounding variables from historical records and interviews alone.

Prospective Cohort StudyIn a prospective cohort study, the effects of a certain variable are plotted over time, and the study becomes an ongoing process. •To maintain validity, all of the subjects must be initially free of the condition tested for.

E.g. An investigation, over time, into the effects of smoking upon lung cancer must ensure that all of the subjects are free of the disease. •It is also possible to subgroup and try to control variables, such as weight, occupation type or social status.•They are preferable to a retrospective study, but are expensive and usually require a long period of time to generate useful results, so are very expensive and difficult.•The prospective cohort study is a great way to study long-term trends, allowing the researcher to measure any potential confounding variables, but the potential cost of error is high, so pilot studies are often used to ensure that the study runs smoothly.

Ambidirectional Cohort Study•The ambidirectional cohort study is the ultimate method, combining retrospective and prospective aspects. •The researcher studies and analyzes the previous history of the cohorts and then continues the research in a prospective manner. This gives the most accurate results, but is an extremely arduous undertaking, costing time and a great deal of money.•The ambidirectional study shares one major drawback with the prospective study, in that it is impossible to guarantee that any data can be followed up, as participants may decline to participate or die prematurely. •These studies need to look at very large samples to ensure that any attributional losses can be absorbed by the statistics

Panel studies allow the researcher to find out why changes in the population are occurring since they use the same sample of people every time. •That sample is referred to as a panel.

•A researcher could for example, select a sample of the SBL students and ask them questions on their future work expectations. •Every year thereafter, the researcher would contact the same people and ask them similar questions and ask them the reasons for any changes in their expectations. •Panel studies suffer from attrition, that is, people drop out of the study for various reasons, for example, moving away from the area of study, dying, deciding not to participate in the subsequent surveys, etc.

ObservationThis involves observing and recording the results of the research, gathering the findings into raw data. •The observation stage involves looking at what effect the manipulated variables have upon the subject, and recording the results. •A social scientist has to ensure that they intervene as little as possible

Data Collection MethodsUnstructured data collection methodsWhen a survey is carried out without a fixed interview schedule or questionnaire, the method used is referred to as unstructured data collection method. •This is normally the case for, for e.g. free interviews or in-depth discussions. •Emphasis is on individual basis. •The purpose of the study is normally to explain individual behaviour rather than to generalize the results to a population, and comparability is not important. •Observation is also an unstructured data collection technique (but it is not a survey).

Structured data Collection MethodsFace to faceThis is probably the most traditional method of the survey research design. It can be very accurate. •It allows you to be selective about to whom you ask questions and you can explain anything that they do not understand. •In addition, you can make a judgment about who you think is wasting your time or giving stupid answers.•There are a few things to be careful of with this approach; firstly, people can be reluctant to give up their time without some form of incentive.•Another factor to bear in mind is that is difficult to ask personal questions face to face without embarrassing people. •It is also very time consuming and difficult to obtain a representative sample.•If you are going to be asking questions door-to-door, it is essential to ensure that you have some official identification to prove who you are. MailThis does not necessarily mean using the postal service; this includes delivering it physically. •This is a good way of targeting a certain section of people and is excellent if you need to ask personal or potentially embarrassing questions.•The problems with this method are that you cannot be sure of how many responses you will receive until a long time period has passed.

Structuring and Designing the Questionnaire•The design of your questionnaire depends very much upon the type of survey and the target audience. •If you are asking questions face to face it is easy to explain if people are unsure of a question. •If your questionnaire is going to include many personal questions then mailing methods are preferable.•Keep your questionnaire as short as possible; people will either refuse to fill in a long questionnaire or get bored halfway through. •If you do have lots of information then it may be preferable to offer multiple-choice or rating questions to make life easier.

Cover Note•It is also polite, especially with mailed questionnaires, to send a short cover note explaining what you are doing and how the subject should return the surveys to you. •You should introduce yourself; explain why you are doing the research, what will happen with the results and who to contact if the subject has any queries.

Type of Question•Multiple choice questions allow many different answers, including don’t know, to be assessed. •The main strength of this type of question is that the form is easy to fill in and the answers can be checked easily and quantitatively; this is useful for large sample groups. •Rating, on some scale, is a tried and tested form of question structure. •This way is very useful when you are seeking to be a little more open-ended than is possible with multiple choice questions. •It is a little harder to analyze responses.

•It is important to make sure that the scale allows extreme views.•Questions asking for opinions must be open-ended and allow the subject to give their own response; you should appear to be as neutral as possible during the procedure. •The major problem is that you have to devise a numerical way of analyzing and statistically evaluating the responses which can lead to a biased view, if care is not taken.

•The order in which you ask the questions can be important. Try to start off with the most relevant questions first.

•Also friendly and non-threatening questions put the interviewee at ease. •Questions should be simple and straightforward using everyday language rather than perfect grammar.•Try and group questions about similar topics together; this makes it a lot quicker for people to answer questions more quickly and easily.•Some researchers advocate mixing up and randomizing questions for accuracy but this approach tends to be more appropriate for advanced market research. •For this type of survey the researcher is trying to disguise the nature of the research and filter out preconceptions.•It is also a good idea to try out a test survey; ask a small group to give genuine and honest feedback so that you can make adjustments.

SAMPLINGSelection of a sample•In a bona fide survey, the sample is not selected haphazardly or only from persons who volunteer to participate. •If it is scientifically chosen so that each person has a measurable chance of selection, the results can be reliably projected to the larger population.•Information must be collected by means of a standardized procedure so that every individual is asked the same question in more or less the same way.•Ethically, confidentiality concerns must be observed, for e.g., using only number codes to link the respondent to a questionnaire and storing the name –to- code linkage information separately from the questionnaire, and refusing to give the names of respondents to anyone outside the research project.•Individual respondents should never be identified in reporting survey findings; completely anonymous summaries, for example, in terms of tables and charts should be given. •Respondents must be asked for their consent to participate in the survey. Their privacy and rights must be observed.

Sampling Methodsi. Two classes of sampling methods 1. Probability Sampling: This is a concept of probability that a certain event will occur if the experiment is to be executed once. Each element of the population has a known positive probability of being selected as an element of the sample.2.Non-probability sampling: This includes all methods of sampling in which the probability of selection of population elements is unknown or undeterminable.

These samples are faster, more convenient and cheaper to apply in practice. They are popular in (1) market research and (2) opinion surveys where speed is of utmost importance.•With these methods, no indication of possible bias and of the error bounds of estimates in respect of population characteristics can be done.•But this does not imply that good results cannot be obtained. –The problem is that the user is unable to give any indication of the reliability of the results that have been obtained. They can somehow also, though rarely, be generalized to the population.

•Social science is often conducted in situations where you cannot select the kind of probability samples used in large scale surveys.

•For e.g., if you wanted to study street children in Mafikeng. There is no list of these children. It is almost impossible to create such a list.

• In addition to that, there are times when probability sampling would not be appropriate even if it were possible. Examples of non probability sampling are; Judgmental non probability sampling or purposive, snowball and quota.

ii. RandomnessThis concept is applied in probability sampling in the process of obtaining a representative sample. E.g. a coin tossing – random selection process or use of random numbers.

a. Probability sampling proceduresi. Simple random sampling (SRS)For SRS, each element or unit has the same probability of being selected, with or without replacement. (i) every element in the population should be clearly and unambiguously identifiable, and (ii) a list of all the elements of the population (sampling frame) should be available. E.g. list of university students. Caution/commenti. In some cases, it is difficult if not impossible to compile a list of all the elements of the population.

ii. A SRS is not necessarily a representative sample of the population. E.g. in a study on the spending pattern of households in a community, a sample consisting of households in for e.g., the highest socio-economic class has the same probability of being drawn as any other specific sample of the same number of households.

ii. Systematic samplingSystematic random sampling can be understood as a method of a sample taken from a list prepared on a systematic arrangement either on the basis of alphabetic order or on house number or any other method. Drawing a SRS can be tedious and time consuming. Systematic sampling is generally quick and easy, and often a much more convenient method of sampling. •The basic principle is that elements are drawn systematically from a complete list of the elements. E.g., if N=nk, where n = sample size and k = an integer.

•The first element to be chosen comes from the first k elements, then every kth element will be included in the sample of size n. The selection interval or length will be equal to k.

Remarks1. A systematic sample works if there is no relationship between the variable (or characteristic associated with the elements of the population) being studied and the order of the elements in the population.2. The use of systematic sampling becomes problematic if there is a periodicity in the values of a relevant variable. E.g. A list of soldiers in the Second World War.

iii. Stratified sampling This method is used when:1. the population is heterogeneous (or has different elements) in respect of the variable or characteristic being studied, and2. the population can be divided into so-called sub populations or strata that are each more homogeneous (or with similar elements) in respect of the relevant variable than the population as a whole.

•The sub-populations or strata should not overlap and should jointly constitute the entire population.•A random sample is drawn from each stratum so that subsamples jointly constitute the total sample.•Estimates become more precise as sampling variation decreasesReasons for stratification are:•To improve precision• administrative convenience• to ensure that every important part of a population is adequately represented in the sample.Factors that play a role in minimizing costs or standard error:1. The size of the strata2. The survey cost per unit within the different strata3. The variation in the relevant variable within the different strata.

Proportional Stratified Sampling•The size of the subsample is proportional to the size of the stratum.•It can lead to unnecessarily large sub-samples from the larger strata and to subsamples from the smaller strata that are too small resulting in wasted money and smaller strata not being adequately represented in the total sample.

Example: Stratifying population in terms of urban areas and rural areas since spending patterns are likely to be different.

iv. Cluster samplingThis sampling method is used in a situation where it is difficult or impractical or even impossible to compile a list for purposes of sampling. E.g. Population of a city.

•Cluster sampling involves the initial drawing of groups of population elements, called clusters.•Then drawing elements from each selected cluster. E.g. Draw a sample of schools first, then pupils from these schools.•One-stage sampling: all elements in the selected clusters are selected.•Multistage sampling: a sub-sample can be drawn from each of the selected clusters.

Reasons for cluster sampling1. When no sampling frame is available.2.Economic and practical reason, avoiding for e.g. traveling long distances to reach one or two persons. Cost in terms of money and time.

•Like in the case stratified sampling cluster sampling requires prior knowledge of the composition of the population.

•The more heterogeneous (in terms of the relevant variable) the composition of the clusters from the elements of the population, i.e. is the greater the variation between the values of the variable associated with the elements within the same cluster, the smaller the standard error and consequently the higher or better the precision of the estimates.

•The smaller the cluster size, the more expensive the survey but the better the precision. Then the compromise will have to be found between these two aspects.

Complex sampling (combination of stratified and cluster sampling)Sampling procedure:

•Stratification: to draw a representative sample and to improve the precision of estimates by forming strata as homogeneous as possible.•Cluster: No complete list – sampling frame•Multistage sampling: Clusters drawn first from each stratum. Then smaller clusters are drawn from the selected clusters etc. Until population elements are eventually drawn from the last clusters. It is a step-by-step design

Non-probability sampling - normally for qualitative research•Estimation of standard error serves no purpose because the estimate cannot be interpreted.

•Non-probability samples do not permit generalization outside the group of sample elements and can be assessed fully by subjective evaluation.Examples: Convenient, Haphazard, judgment or purposive and quota sampling (combination of convenient and judgment sampling).

Convenient Sampling •Obtaining people or units that are conveniently available •E.g. it would be more convenient and economical to set up an interviewing booth from which to intercept consumers at a shopping mall.•A lecturer using his/her students for a research study•Note: Projecting or generalizing to the results beyond the specific sample is inappropriate.

Judgment or Purposive sampling•A non probability sampling procedure when an experienced researcher selects the sample based on his/her judgment about some appropriate characteristic required of the sample member.•Researchers select samples that satisfy their specific purpose even if they are not fully representative•E.g., CPI is based on a judgment sample of market basket items•A fashion manufacturer selects a sample of key accounts that it believes are capable of providing information needed to predict sales•Can be used to predict election results

Quota Sampling•Probability sampling may underrepresent or overrepresent certain subgroups in the population•The researcher may wish to ensure that certain subgroups are included proportionately to the sample•The purpose is to ensure that the various subgroups in a population are represented on pertinent sample characteristics to the exact extent that the investigator desires•He/she has a quota to achieveAdvantages:•Speed of data collection, lower costs and convenience•Carefully selected data collections may provide a representative sample of the various subgroups within a population•May be appropriate if the researcher knows that certain demographic group is more likely to refuse to cooperate with a surveySnowball Sampling•Involve using a probability sampling for an initial selection of respondents and then obtaining additional respondents through information provided by the initial respondents•Used to locate members of rare population by referrals•Bias is likely to occur because the person suggested by someone also in the sample has a higher probability of being similar to the first person

QUALITATIVE APPROACH

When to choose Qualitative ResearchQualitative research serves the following purposes:•Descriptive – reveal nature of certain situations, settings, processes, relationships, system or people.•Interpretation – to gain new insights about a phenomenon, develop new concepts and theoretical perspectives, etc and discover the problem that exists within the phenomenon.•Verification – it allows the researcher to test the validity of certain assumptions, claims, theories or generalizations within the real world•Evaluation – a means through which a researcher can judge the effectiveness of a particular policy, practice or innovation.

Qualitative Research Designs (Leedy & Ormrod, 2005) •Case study, Ethnography, Phenomenological, Grounded theory, and Content analysis

•We dig deep to get a complete understanding of the phenomenon.•We collect different forms of data and examine them from various angles to construct a rich and meaningful picture of a complex, multifaceted situation. There are several different approaches but they:• all focus on a phenomenon in its natural setting in the real world.•involve studying the phenomenon in all its complexity in a multifaceted and all its dimensions.The researcher must keep his/her perceptions, impressions and biases to him/herself. What matters is to get the truth.

Brief notes on the Research DesignsCase StudyA particular event, programme or individual studied in depth.e.g., a medical researcher studying the nature, course and treatment of a rare illness. Focuses on a single case - can be generalized to similar situations.May focus on 2 or 3 cases to make comparisons, build a theory or propose generalization.

Case studies are detailed investigations of individuals, groups, institutions or other social units. The researcher conducting a case study attempts to analyze the variables relevant to the subject under study (Hungler & Polit, 1983).

The principle difference between case studies and other research studies is that the focus of attention is the individual case and not the whole population of cases.

Most studies search for what is common and pervasive. However, in the case study, the focus may not be on generalization but on understanding the particulars of that case in its complexity. A case study focuses on a bounded system, usually under natural conditions, so that the system can be understood in its own habitat (Stake, 1995; 1988).

Method•Extensive data, Observation, Interviews, Documents, etc, Past records•Audiovisual materials (photographs, video tapes, audio tapes)

The researcher may spend extended period of time on the site and interact with the participants.

Data analysis•Organizing of details about the case•Categorizing of data – cluster into meaningful groups •Interpretation of single instances – specific documents, occurrences•Identification of patterns – underlying themes characterizing the case more broadly•Synthesis and generalization – an overall portrait of the case is constructed. Conclusion and implication beyond the case.•The researcher must look for convergence from a triangulated study, that is, separate pieces of data must point to the same conclusion.

Writing the ReportIn report writing, the researcher records details about the context surrounding the case, that is, information about the physical environment and historical, economic and social factors that have a bearing on the situation.

This helps other researchers who read the report draw conclusions about the extent of generalization to other situations.

•Rationale – worthiness of in-depth study and contribution about the real world.•Detailed description of the facts related to the case•Description of data collected, i.e., What observations, whom interviewed, what documents examined, etc.•Discussion of the patterns found – any trends, themes, personality characteristics, etc. You have to convince the reader by also describing contradictory information as well.

•Must be as complete and unbiased as possible•A connection to the larger scheme of things. In what way does the case study contribute to the knowledge about some aspects of the human experience?•Compare to previous studies, etc.

ETHNOGRAPHY•The researcher looks at the entire group that shares a common culture in depth.•Natural setting•Length of time period – even up to several years.•Focus is on everyday behaviours (e.g. interactions, language, rituals) with an intent to identify:•Cultural norms •Beliefs•Social structures•Other cultural patterns.Mainly done in sociology, psychology and education.

Method•Site – based field work•Prolonged engagement with people to observe and record processes..•Better when the researcher is a stranger to avoid biasTo gain entry the researcher often go through a gatekeeper such as a tribal chief, the person who can provide a smooth entrance into the site.

•The researcher must be open about why he/she is there.•Initially, the researcher uses a big net approach, intermingling with everyone and getting an overall sense of the cultural context.

•Gradually he identifies key informants to provide relevant information.•Participant observation can do; the disadvantage however is that the researcher can become emotionally involved and lose the ability to assess the situation accurately.

•Throughout the field work he/she must be a careful observer, interviewer and listener while taking extensive field notes.•Lengthy conversations and significant events can be recorded using audiotapes or videotapes.•Can also collect artifacts and records e.g. accounting ledgers.•Great patience and tolerance and being sociable are necessary.

Data Analysis•Descriptive – Data organized into logical structures•Describing events in chronological order•Describing a typical day in the life of the group or an individual

•Focusing on a critical event•Developing a story, with plots and characters.•Analysis – data categorized according to their meanings, patterns, regularities and critical events identified.

•Interpretation – The general nature of the culture is inferred from the categories of meanings and patterns identified in 2.•Existing theoretical frameworks may help

Note: Total objectivity is impossible.

Report writing•Often personal, literary narrative designed to engage the reader’s attention and interest.

It Includes:•Introduction – rationale and context.•Present your research question•Describe the nature of the study•Importance of the study

•A description of the setting and methods used•Describe the group and systems and rituals, the name of the place, etc.•An analysis of the culture studied

•Describe the patterns and themes observed, norms and conventions for behaviour, the social hierarchy, belief system.•Present evidence to support your claimUse the participants’ actual words

Conclusion •Relate findings to the research question and concepts and theories in the discipline•Avoid making judgments, (even small changes in the wording can make a significant difference in this regard).•Should be sufficiently detailed.

•Refers to a person’s perception of the meaning of an event.•Attempts to understand people’s perceptions, perspectives and understandings of a particular situation. E.g. experiences of people caring for a dying relative, living in abusive relationship.

•By looking at multiple perspectives, on the same situation the researcher can make some generalization.

Method•Carefully selected sample of participants•Lengthy interview e.g., 1 or 2 hrs.•Often very unstructured

•The researcher listens closely as participants describe their daily experiences related to the phenomenon.•Typically an interview tool like informal conversation - as participants do most of the talking.

PHENOMENOLOGY

Data analysisTo identify common themes:

Steps:•identify statements that relate to the topic•The researcher breaks information into small segments (e.g., phrases or sentences) that each reflects a single, specific thought.•Group statements into ‘meaning units’ – categories.•Seek divergent perspectives•Construct a composite•Develop overall description of the phenomenon or people’s experience.•The focus is on common themes.

Research report•No specific structure•Present your research problem or question•Describe the methods used for data collection and analysis•Draw conclusions•Relate your findings to an existing body of theory and research.•Discuss any practical implications of the findings.

GROUNDED THEORY•Least likely to start from a particular theoretical framework•Major purpose of this approach is to begin with the data and use them to develop a theory.•Term ‘grounded’ gives an idea that the theory is derived from and grounded in data collected in the field rather than taken from literature.•Focuses on a process related to a particular topic, with ultimate goal of developing a theory about that process.

Method•Field based•Interviewing, observations, documents, etc are used•Data collected must include the perspectives and voices of the people being investigated.

•Cases are selected by a sampling process in which the researcher identifies new cases that are similar to previous cases. •When these cases generate no new insights, the process is repeated with newly selected cases that yield different insights again until no new insights are noted.

Data analysis•Categorize to classify the data•Identify interrelationships

•Data analyzed may lead to later data collection for revision.•Theory developed includes numerous concepts and interrelationships.•The theory is written in the form of a verbal statement, visual model or series of hypotheses explaining the phenomenon.

The research report•A description of the research question•A review of the related literature•A description of the methodology and data analysis done•A presentation of your theory•A discussion of implications•Show how your theory is similar or dissimilar to existing theory•Explain how it is related to existing body of knowledge•Give implications

CONTENT ANALYSIS

•A detailed and systematic examination of the contents of a particular body of material for the purpose of identifying patterns, themes or biases.•Used in a wide range of disciplines.•Can be used with another approach

Method•identify the specific body of material to be studied•a random sample may be used•Define the characteristics or qualities to be examined in precise, concrete terms.•You may break down items of a complex material into small, manageable segments to be analyzed separately.•Scrutinize the material •When the material is entirely objective, one single judgment is enough, but if subjective, more judgments, may be, 2 or 3 are required, and then a composite of the judgments is used.

Data analysis•Tabulate the frequencies of each characteristic found – implying the use of both quantitative and qualitative approaches.•Appropriate statistical analysis can then be done on the frequencies to interpret the data as they reflect on the research problem.

Research reporting•Describe the body of the material and sampling procedure used•Give a precise definition and description of the characteristics you looked for.•Describe the coding or rating procedure used•Tabulation and graphing – report the frequencies and percentages obtained.•Give a description of the patterns and trends that the data reflected.

How to analyse qualitative data•It depends upon the type of questions used. •Analyzing results for a case study tends to be more opinion based than statistical methods. •The usual idea is to try and collate your data into a manageable form and construct a narrative around it. •Use examples in your narrative whilst keeping things concise and interesting. •It is always a good idea to assume that a person reading your research may not possess a lot of knowledge of the subject so try to write accordingly. •Unlike a scientific study which deals with facts, a case study is based on opinion and is very much designed to provoke reasoned debate. •There really is no right or wrong answer in a case study. •For multiple choice questions it is a matter of counting up the answers to each question and using statistics for analysis.•Rating type question require a little more work but the follow broadly the same principle.•For opinion questions, you can devise some way of judging the responses numerically.•The next step is to devise which statistical test you are going to use.

Data analysis for quantitative data

•Use of statistical methods

For e.g.:•Chi-square test is used to test relationships or dependency between variables, •t-test is used to compare two groups by comparing their mean values, •ANOVA is used to compare more than two groups,•Correlation and Regression analysis is used to test relationships, •Factor analysis is used to study or identify factors of phenomena, etc.

Significance Test•To test a hypothesis, quantitative research uses significance tests to determine whether the hypothesis is right. •The significance test can show whether the null hypothesis is more likely correct than the alternative hypothesis or vice versa.

•The t-test is one of many statistical significance tests, which compares two supposedly equal sets of data to see if they really are alike or not. •The t-test helps the researcher conclude whether a hypothesis is supported or not. •The significance test is the process used, by researchers, to determine whether the null hypothesis is rejected, in favor of the alternative or not. •The test involves comparing the observed values with theorized values. •The tests establish whether there is a relationship between the variables, or whether pure chance could produce the observed results.

Statistically Significant ResultsStatistically significant results are those that are interpreted not likely to have occurred purely by chance and thereby have other underlying causes for their occurrence.

- Whenever a statistical analysis is performed and results interpreted, there is always a finite chance that the results are purely by chance. •Mistakes such as measurement errors may cause the researcher to misinterpret the results. •However, the probability that the process was simply a chance encounter can be calculated, and a minimum threshold of statistical significance can be set. •If the results are obtained such that the probability that they are simply a chance process is less than this threshold of significance, then we can say the results are not due to chance.•Common statistically significant levels are 5%, 1%, etc.

•In terms of null hypothesis, the concept of statistical significance can be understood to be the minimum level at which the null hypothesis can be rejected.

•This means if the researcher sets his statistical significance level at 5% and the probability that the results are a chance process is 3%, then the experimenter can claim that the null hypothesis can be rejected.•In this case, the experimenter will call his results to be statistically significant. Lower the significance level, higher the confidence. •While determining significant results statistically, it is important to note that it is impossible to use statistics to prove that the difference in levels of two parameters is zero.

•This means that the results of a significant analysis should not be interpreted as meaning there was no difference. •The only thing that the statistical analysis can state is that the study failed to find any difference.

Interpretation•Drawing a conclusion is based on several factors of the research process, not just because the researcher got the expected result. •It has to be based on the validity and reliability of the measurement, how good the measurement was to reflect the real world and what more could have affected the results.

•The observations are often referred to as 'empirical evidence' and the logic/thinking leads to the conclusions. •Anyone should be able to check the observation and logic, to see if they also reach the same conclusions.•Errors of the observations may stem from measurement-problems, misinterpretations, unlikely random events etc.•A common logical error for beginners, is to think that correlation implies a causal relationship, which is not necessarily true.

Errors in Research•Logically, it is possible to make two types of errors when drawing conclusions in research: •Type 1 error is when we reject the null hypothesis when the it in fact correct.•Type 2 error is when we accept it when it is in fact wrong

Evaluation•After analysing the data, the researcher then evaluates the study. •This involves critically evaluating any weaknesses and errors in the design, which may have influenced the results.

Generalization•Generalization is to which extent the research and the conclusions of the research apply to the real world. •Good research will reflect the real world, since we can only measure a small portion of the population at a time.

Conclusions This stage is where, technically, the hypothesis is stated as proved or disproved. •For any research project, drawing conclusions is the final, and most important part of the process.•Whichever reasoning processes and research methods were used, the final conclusion is critical, determining success or failure. •Success or failure is not a measure of whether a hypothesis is accepted or refuted, because both results still advance scientific knowledge.•Failure is poor research design, or flaws in the reasoning processes, which invalidate the results.

•As long as the research process is robust and well designed, then the findings are sound.•The key is to establish what the results mean. How are they applied to the world? •Be self critical whether your results showed what you expected or not. •Any survey has flaws in its method so it is always a good idea to show that you are aware of these. •If your survey gave unexpected results explain the possible reasons for why this happened and suggestions for refining the techniques and structure of your survey next time.•As long as you have justified yourself and pointed out your own shortcomings then your results will be relevant and you should receive a good result.

Research Implications or Recommendations•The final stage is the researcher’s recommendations based upon the results. •This area of the research process can be based around the researcher’s personal opinion, and will integrate previous studies. •It is critical in determining the direction taken by the scientific community, but the researcher will have to justify their findings.

Summary•The key to drawing a valid conclusion is to ensure that the deductive and inductive processes are correctly used, and that all steps of the scientific method were followed. •If your research had a robust design, questioning and scrutiny will be devoted to the conclusion, rather than the methods.

What has been learnt?•Generally, a researcher will summarize what they believe has been learned from the research, and will try to assess the strength of the hypothesis. •Even if the null hypothesis is accepted, a strong conclusion will analyze why the results were not as predicted.•In observational research, with no hypothesis, the researcher will analyze the findings, and establish if any valuable new information has been uncovered.

Future Research•Very few studies give clear-cut results, and most research uncovers more questions than answers. •The researcher can use these to suggest interesting directions for further study. •If, for e.g., the null hypothesis was accepted, there may still have been trends apparent within the results.•These could form the basis of further study, or study refinement and redesign.

DESCRIPTIVE RESEARCH DESIGNS

•A descriptive research design is a scientific method which involves observing and describing the behavior of a subject without influencing it in any way.•Many scientific disciplines, especially social science and psychology, use this method to obtain a general overview of the subject.

•Some subjects cannot be observed in any other way; for example, a social case study of an individual subject is a descriptive research design and allows observation without affecting normal behavior.

•It is also useful where it is not possible to test and measure the large number of samples needed for more quantitative types of study. •It is also used by market researchers to judge the habits of customers, or by companies wishing to judge the morale of staff.•The results from a descriptive research can in no way be used as a definitive answer or to disprove a hypothesis.

Advantages•The subject is being observed in a completely natural and unchanged natural environment. •A good example of this would be an anthropologist who wanted to study a tribe without affecting their normal behavior in any way.

•Descriptive research is often used as an exploratory study to more quantitatively research designs, the general overview giving some valuable pointers as to what variables are worth testing quantitatively. Disadvantages•Because there are no variables manipulated, there is no way to statistically analyze the results. •Many scientists regard this type of study as very unreliable and ‘unscientific’.

QUALITATIVE RESEARCH DESIGN•Qualitative research design is a research method used extensively by researchers studying human behavior and habits.

•Qualitative research is often regarded as a precursor to quantitative research, in that it is often used to generate possible leads and ideas which can be used to formulate a realistic and testable hypothesis.

•This hypothesis can then be comprehensively tested and mathematically analyzed, with standard quantitative research methods.

Design•The design of qualitative research is probably the most flexible of the various research techniques. •There is no standardized structure.

•Case studies and survey designs are the most commonly used methods.

Advantages•Qualitative techniques are extremely useful when a subject is too complex to be answered by a simple yes or no hypothesis. •These types of designs are much easier to plan and carry out.•Qualitative research methods are not as dependent upon sample sizes as quantitative methods. Normally, small sample sizes are used. Disadvantages•Whilst not as time or resource consuming as quantitative experiments, qualitative methods require a lot of careful thought and planning, to ensure that the results obtained are as accurate as possible. •Qualitative data cannot be mathematically analyzed in the same comprehensive way as quantitative results, so can only give a guide to general trends.

•It is a lot more open to personal opinion and judgment.•Any qualitative research design is usually unique and cannot be exactly recreated, meaning that they do lack the ability to be peer reviewed.

DATA ANALYSIS OF QUALITATIVE DATA IN GENERAL

•Interview questions and responses are typically tape-recorded and then transcribed verbatim before analysis is begun.

•Qualitative researchers often categorize data into patterns as the primary basis for organizing and reporting results.

Transcription is extremely time-consuming (Marlow, 1993). Due to the large amount of data that can be generated in qualitative research, a data reduction process must be used to aid analysis.

This procedure includes: organizing the data; identifying emerging themes, categories, and patterns; and testing hypotheses against the data.

Either “indigenous” or “analyst-constructed” typologies may be constructed. •In indigenous categories, the language of respondents is used to label types of processes (Marshall & Rossman, 1989; Patton, 1990). •In analyst-constructed categories, the researcher attaches a label to observed recurring events.

Narrative descriptions of data collected through interviews, observations, and case records are also used in qualitative analysis.

Content analysis is often used in qualitative and quantitative research methods.

Some researchers view content analysis as a technique to quantify manifest (surface-level) descriptive data (Allen-Meares, 1985), in which categories are developed, content is coded, and category counts are conducted.

Qualitative content analysis typically does not transform the content into numeric patterns; instead, recurrent themes, and typologies and illustrations of particular issues, are used.

The following are interpretive techniques:

Observer impressionThe most common analysis of qualitative data is observer impression. Expert or bystander observers examine the data, interpret it via forming an impression and report their impression in a structured and sometimes quantitative form.

Coding •Helps to interpret the data by organizing the data and providing a means to introduce the interpretations of it into certain quantitative methods. •In most cases, coding requires the analyst to read the data and demarcate segments within it.

Each segment is labeled with a “code” – usually a word or short phrase that suggests how the associated data segments inform the research objectives.

•When coding is complete, the analyst prepares reports via a mix of: summarizing the prevalence of codes, discussing similarities and differences in related codes across distinct original sources/contexts, or comparing the relationship between one or more codes.

•Computer programmes can assist in this regard.

•The criticism of the coding method is that coding seeks to transform qualitative data into quantitative data, thereby reducing the detail (i.e. its variety, richness and individual character). •Careful definition of the codes and linking them to the underlying data can address this concern.

Recursive abstraction Some qualitative datasets are analyzed without coding.

Datasets are summarized, those summaries are then further summarized, and so on.

The end result is a more compact summary that would have been difficult to accurately portray. 

•The common criticism of this method is that the final conclusions are several times removed from the underlying data such that poor initial summaries will yield an inaccurate final report.

•What researchers do is to document the reasoning behind each summary step and cite examples from the data where statements were included and where statements were excluded from the intermediate summary.

Mechanical techniques The researcher uses a computer to scan and sort large sets of qualitative data by counting the same words or phrases within the data.

•This technique is particularly suitable for datasets that are too large for a human to effectively analyze, or where analysis would be cost prohibitive relative to the value of information they contain.

•The criticism of the technique is the absence of a human interpreter.

MIXED METHOD APPROACH

When the phenomenon being investigated is not well understood, a qualitative research can be used first to generate preliminary hypotheses, and then quantitative research is used to test specific hypotheses.

For comprehensive studies, it is better to use both approaches (i.e. qualitative and quantitative), a situation where, the quantitative method helps to test hypotheses and to make the study more objective and the qualitative method helps to give a complete understanding or in-depth information on the phenomenon being studied – in all its dimensions.

•Complex studies, having many different research questions may use both approaches to answer particular questions or to address particular research problems.

•E.g., poverty is multidimensional in nature, i.e., it has social, political and economic dimensions. •So, a poverty study may need both approaches to be studied – a situation where the qualitative research methods are used to investigate the social and political issues and help the voice of the poor to be heard and quantitative methods are used to study the economic issues.

According to Lee (1999), within a single study multiple qualitative and quantitative techniques that involve complementary data-gathering activities can be applied that compensate for the weaknesses of individual tactics.

The data becomes more comprehensive and quite informative.

E.g. The factors affecting an organizational phenomenon can be quantitatively investigated – using a field experiment and regression analysis and qualitative techniques used to inform about additional, little known variables, processes and conditions that might surround the effects investigated by the quantitative techniques.

•Normally a semi-structured questionnaire is used to include both closed and open-ended questions.

Note:Social experiences and the realities of the world are multidimensional and so if phenomena are viewed only along a single dimension we cannot have a complete picture of what is going on around us.

•Qualitative empirical research tends to expose the complexity of real life experience.•The use of mixed methods and a multidimensional approach allows the researcher to frame questions which precisely focus on how different dimensions and scales of social existence are related.

•The particular strength of qualitative research lies in the knowledge provided regarding the dynamics of social processes, change and social context, and in its ability to answer ‘how’ and ‘why’ questions in those domains.

•There are two core elements to the logic of qualitative explanation: one relates to a qualitative logic of comparison, e.g., between cases, situations, contexts, over time, etc and the second relates to the significance of context.

•Understanding how social processes and phenomena are embedded within specific contexts makes possible the development of cross-contextual generalizations.

This entails the use of contextual explanation, where emphasis is on explaining how different dimensions of context together link up together with the processes or questions driving the study.

Using mixed methods to ‘triangulate’ or to corroborate each other suggests an integrated framework, where each method and form of data is used to highlight a specific part of the picture.

There might however be tensions arising from differences in approaches to data collection because of using different sets of assumptions.

To overcome any such potential difficulty the solution is in how explanations are done.

Explanations do not have to be internally consistent to have a meaning and capacity to explain.

If indeed the realities of the world are multidimensional – political, social, cultural, economic, etc, then explanations arising from mixed data-collection methods would be likewise (see Cho and Trent, 2006; Dixon-Woods, et. al. 2006, Moran-Ellis, 2006; Mason, 2006 in Kimani, 2009).

Remember:•Using a quantitative research design is an excellent way of finalizing results and proving or disproving a hypothesis, and

•Scientific experiments are useful for testing the data gained by a series of qualitative experiments, leading to a final answer, and a narrowing down of possible directions for follow up research to take.

Research Bias•Research bias is a process where the scientists performing the research influence the results, in order to portray a certain outcome.•Some bias in research arises from experimental error and failure to take into accounts all of the possible variables.

•Other research bias arises when researchers select subjects that are more likely to generate the desired results. •Research bias is the one factor that makes qualitative research much more dependent upon experience and judgment than quantitative research.•Any design process involves understanding the inherent biases and minimizing the effects.

•In quantitative research, the researcher tries to eliminate bias completely whereas, in qualitative research, it is all about understanding that it will happen.

Design bias•Design bias is introduced when the researcher fails to take into account the inherent biases liable in most types of experiment. •Some research bias is inevitable, and the researcher must show that they understand this, and have tried their best to lessen the impact, or take it into account in the statistics analysis.

Selection Bias•This is sampling bias that occurs when the process of sampling actually introduces an inherent bias into the study.•There are two types of sampling bias, based around those samples that you omit, and those that you include:

Omission Bias•This research bias occurs when certain groups are omitted from the sample. •Omission bias is often unavoidable, so the researchers have to incorporate and account for this research bias in the research design.

Inclusive Bias•Inclusive bias occurs when samples are selected for convenience. •This type of bias is often a result of convenience where, for e.g., volunteers are the only group available, and they tend to fit a narrow demographic range.•There is no problem with it, as long as the researchers are aware that they cannot extrapolate the results to fit the entire population.

Procedural Bias•Procedural bias is where an unfair amount of pressure is applied to the subjects, forcing them to complete their responses quickly.•For e.g., employees asked to fill out a questionnaire during their break period are likely to rush, rather than reading the questions properly.

Measurement Bias•Measurement bias arises from an error in the data collection and the process of measuring. •In quantitative studies, a faulty scale would cause an instrument bias and invalidate the entire experiment. •In qualitative research, the scope for bias is wider and much more subtle, and the researcher must be constantly aware of the problems.•Subjects are often extremely reluctant to give socially unacceptable answers, for fear of being judged. •For e.g., a subject may strive to avoid appearing homophobic or racist in an interview. •This can skew the results, and is one reason why researchers often use a combination of interviews, with an anonymous questionnaire, in order to minimize measurement bias.•Particularly in participant studies, performing the research will actually have an effect upon the behavior of the sample groups. •This is unavoidable, and the researcher must attempt to assess the potential effect.

•Instrument bias is one of the most common sources of measurement bias in quantitative experiments.•This is the reason why instruments should be properly calibrated, and multiple samples taken to eliminate any obviously flawed or aberrant results.

Interviewer Bias•This is one of the most difficult research biases to avoid in many quantitative experiments, which rely upon interviews. •The interviewer may subconsciously give subtle clues in with body language, or tone of voice, that subtly influence the subject into giving answers skewed towards the interviewer’s own opinions, prejudices and values.•The use of some form of anonymous process can eliminate the worst effects.

Response Bias•Conversely, response bias is a type of research bias where the subject consciously, or subconsciously, gives response that they think that the interviewer wants to hear. •The subjects may also believe that they understand the study and are aware of the expected findings, so adapt their responses.•The amount of information given to the subject must be restricted, to prevent them from understanding the full extent of the research.

Reporting Bias•Reporting Bias is where an error is made in the way that the results are disseminated in the literature.•With the growth of the internet, this type of research bias is becoming a greater source of concern. •The main source of this type of bias arises because positive research tends to be reported much more often than research where the null hypothesis is upheld. •Increasingly, research companies bury some research, trying to publicize favorable findings.