struggling with research methodology

Home Forums Default Forum struggling with research methodology

Viewing 12 posts - 1 through 12 (of 12 total)
  • Author
  • #5018

    Hi everyone, currently i’m doing ma honours in management and it’s very difficult for me to do my research because i’v never done it before, its ma first time. So can anyone plz help me, and plz make it clear to me what are the most fundamentals and critical issues that are so important i need to take into account when i’m doing ma research and steps that i hv 2use to do a proper reseach.

    Pat Bazeley

    Probably you could start by using an appropriate form of written language. Then you might check out available coursework, and read some of the hundreds of introductory books that are available.


    Thanks, I will take that into consideration. The most difficult part is to select a topic because we donot have much time to identify one and it is highly impossible to go through every topic because this might lead to, to much confusion and time wastage but to you Pat thank you so much.

    Pat Bazeley

    Given you have to spend a fair bit of time working on it, it is important to pick a topic that you find interesting – something from your undergraduate work that fascinated you perhaps, or something from life experience (as long as you can distance yourself from the experience sufficiently). It’s also an issue of what you want to achieve by doing it. The other thing to take into consideration is who will be supervising your work and guiding you if you choose that topic – choose one that means you will end up with someone you can relate to and who is skilled and can help you, and also make sure the topic is of interest to that person as well.

    Harriet Baulcombe

    Dear Thembeka,

    There are a wealth of books available which walk you step by step through the process. You might want to look at one of the ones listed on the SAGE website

    Kind regards,

    Dr. James Lani


    If you need assistance with your research methodology, I would be happy to have a free 30-minute consultation with you to discuss your specific research. Contact me at my website or email me directly at

    My Credentials
    Information on Statistics Solutions
    Methodology Page
    How to Select the Appropriate Analysis


    I have to first choose a topic and compile a short document on my topic of interest, in that case I will be allowed to see my supervisor and discuss on what I have or have compiled. It is then where my supervisor will have a say on the topic i have chosen based on the short document. But however the supervsor can say I won’t be able to make it on that particular topic after my effort because of that document, meaning I have to be very good. Which technique is best, the qualitative or the quantitative? and the sample, how do i know the sample i want to study and the sample size ? Anyway i will try my best and thank you once again Pat.


    Thank you Harriet. I will do that and try the website


    Research Methodology
    Without prejudice to whatever form of shapes of enquiry given to research methods, a narration is made about the current practice in research methods

    Research is a term that needs to be understood in all its perspectives, especially by those trying to do carry out a set of activities under a formal setup available with the various universities. Literature has no bounds for material trying to bring out the features associated with research. As a small contribution to the available material an effort is made to make research workers from Universities feel comfortable, by providing various concepts associated with research and the methods to be adopted in a guideline framework.

    Research may be defined as an activity leading to insight, intuition, or knowledge gained by a diligent perception and to a systematic inquiry or investigation into a subject in order to validate such perception. Research includes three phases.
    1. Perception
    2. Experiment
    3. Inference.

    By ‘Perception’ we mean a single unified awareness derived from certain processes, either explicit or implicit, while a stimulus is present. The main consequence is ‘awareness’ i.e., a cognition of something and a possible notion about its existence. The stimulus, which is present, makes one to take up some sequence of steps to acquire information relating to that subject with a view to verify that awareness.
    By ‘Experiment’ we generally mean the conduct of an experiment, i.e. an act or operation for the purpose of discovering something unknown. The perceived problem may lead one to have a complete knowledge about the basic assumptions born out of the activities leading to perception. The experiment will be to realize those assumptions and see the consequent outcomes leading to some information. Then it is natural thing to see if such information validated the perceived through a process of inference.

    By ‘inference’ we mean the act or process of deriving logical conclusions from premises known or assumed to be true.

    Logic and Reasoning:

    The term inference may be taken to mean a process of arriving at conclusions in a logical way. There are two possible ways for the same and they are called as
    Deduction involves constructions that make one to jump from constructs in rational manner to reach the conclusion.

    Induction is a process of observing partially and making a logical and intelligent guess. Naturally, since this is a guess certain amount of error is possible in conclusions.

    Deduction requires
    A general statement/construct Major premise
    A particular statement/construct Minor Premise
    Conclusion Conclusion

    Induction involves
    Observe Partially Observe a Sample
    Through Inference In a logical and intelligent way
    Generalize findings Guess the results for all (Population)

    Type of Research:
    Depending upon the technique used in research there are two types of research.
    1. Quantitative Research
    2. Qualitative Research

    By ‘Quantitative Research’ we mean a set of activities involving the measurement of related concepts in quantitative terms. Generally concepts are measured from a partial set of items related to the issue, otherwise called as a sample, and using a process of induction the results are inferred.

    By ‘Qualitative Research’ we mean research involving certain concepts, where the concepts are considered for their inherent relations using arguments consistent with the accepted notions of logical reasoning so as to explain and establish certain propositions. It may be noted that some of the concepts considered may be attributes having some qualitative characteristics. It is to be understood that the topic of research, which generates a set of questions are to be answered in an appropriate sequence, constructing a reasonable (Logical) succession among the concepts so that the objectives are fulfilled using narration in a story telling framework. This may be stated as ‘substantiating and validating’ the associated hypotheses through arguments. In early days such a type of inquiry was called as ‘substantive’ research. Generally, one uses ‘deduction’ in an intelligent way to reach the goal. Naturally, there is no place for generalization as the results are deduced using deductive arguments.
    These are considered in detail in sequence.

    Research and Decisions:
    Research involves inference, a way of arriving at conclusions after observation. Observations provide a situation where the researcher is facing a problem of choosing between two or among more alternative possible consequences. Based on observations researcher has to take decisions regarding the problem being studied. For example, the researcher might study a sample of branches of a nationalised bank; he/she will have to say whether the performance of the nationalised bank is good or bad. There are two possible answers; researcher has to choose one of them based on observations using some intelligent procedure. It is possible, in certain situations there may be more than two possible alternatives; in the same example, the alternative possibilities may be excellent, good, normal and poor.

    This problem of choosing one alternative from a set of specified alternatives is called as the ‘decision problem’. The choice of the alternative must be made in an optimal way.

    The next question will be ‘What this optimum means’. The problem of choosing one among the available alternative courses of actions is to be done by the researcher with partial information. This is due to the researcher being restricted from observing the entire population due to practical considerations. Naturally, when a decision is taken without complete information, it will be just an inference leaving a certain amount of error in the result resulting in a loss. How to choose? It depends upon certain other considerations.

    This may be understood with a structured discussion. We may consider a simple Decision problem. Suppose one wants to decide whether he has to take an umbrella when he sets out for an outdoor work, it is easy to note that there are two alternatives, ‘Take’ or ‘Do Not Take’. Also, observe that this has to be done with knowledge about the weather conditions. Assume that the weather will have three possibilities; ‘Sunny’, ‘Rainy’ ands ‘Cloudy’. Then the person has three possibilities, ‘Knows the condition of the weather completely – Full Knowledge’, ‘Knows the condition of the weather in a Probability sense – Partial Knowledge’ and ‘Knows nothing about the weather – No Knowledge’. In the first case, there is no problem in the choice i.e. to decide. The second case decision is made using probabilities of the type of weather on that day using available information, which requires some effort. The third one has no information and hence decision will be difficult. The first case is called ‘Decision under Certainty’, the second one ‘Decision under Risk’ and the third one ‘Decision under Uncertainty’.

    Empirical research falls in the second category. Where a research worker, who perceives some problem, is interested to validate some statements called ‘Hypotheses’ associated with the problem after conducting some experiment. From the experiment data is generated and partial knowledge is gained about problem situation. Then using a process of inference decisions are made, thus suggesting that research works come under problems of Decision under Risk.

    Nature of Research:

    The nature of research depends upon the type of problem being studied. They may be stated as;
    1. Reporting
    2. Exploratory/Explanatory
    3. Descriptive
    4. Predictive.

    Reporting is the simplest form of research. This is expected to give a summary of related information and if data is used a summary using them needs to be provided. Related statistics, if any, will be provided and a report generated. No inference is required as n results are expected to be provided. This requires the sources of data and related literature. The purpose of this activity is to make one knowledgeable about the domain of research. In formal research programs, this is done initially to make the research worker familiar with the problem.

    Descriptive Study is another elementary form of research which will be the form of enquiry when the problems to be addressed consist of questions involving “who, when, what and where” and sometimes “how”. This will be a useful when one is concerned with profiling a group using some concepts. In quantitative studies this will involve collection of data. Qualitative studies may use narratives for achieving the results.

    Exploratory/Explanatory studies may have a subtle difference. While exploratory studies address the question “Why”, the explanatory studies try to use some well founded theory to frame appropriate hypotheses in the light of such explorations to account for the validity of the hypotheses. Also, this may require relations among concepts under a “Cause-Effect” framework. Quantitative studies may require measurements of concepts in quantitative terms and use them under a statistical inference framework. This is an example of using inference for arriving at results. In qualitative (Substantive) studies explanations are generally achieved by using a sequence of arguments to deduce the results.

    Predictive studies involve higher order capabilities for inference. This will require all other forms of research to arrive at concepts and their relationship.

    These are to be taken differently according to the research interest. While some of them are self explanatory for some topics in social sciences, others may be more explained and useful for disciplines like Economics, Psychology. Further considerations are also to be taken with this restriction.


    Whatever be the form of research, the whole process starts with a cognition of the problem in a manageable way. This cognition is seen to be best achieved by using a model. Lot of philosophical considerations have taken place before the current scenario evolved. Model is a term defying a definition. However an idea of the models and knowledge about them are very much important in more than one sense. While it paves a convenient platform for research, it also provides knowledge about the possible types of studies.

    Model is a term to mean representation. A research problem may be visualised as a system involving some components with specific properties and capabilities. Explaining such a system in simple terms may be very difficult. A collection of ideas relating to “Model” will be highly useful. This is attempted by making an effort to list all possible types of models and their requirements.

    Models can be classified in different ways.

    Models by Type:
    There are three types of models
    1. Iconic models – the system is explained in terms of physical representation using a scaled up or scaled down principle.
    2. Analog models – a complicated system is explained in terms of a simplified system that has an equivalent behaviour as the basic system
    3. Symbolic Models – the system is explained using symbols to represent the components. There are two possibilities here.
    i. Verbal Models – involving a simple verbal explanation using a story or construct.
    ii. Abstract Models – involving symbols and equations as in mathematics.

    Models by Purpose:
    Again models can be classified into three based on their nature. They are
    1. Descriptive Models – the representation is restricted only to the description.
    2. Predictive Models – have the capability to predict the behaviour of a concept in terms of other cognizable concepts.
    3. Normative Models – which are generated to optimize some objective within allowed roles for the related concepts.

    Models by Nature:
    Models can be classified into two depending upon the nature of the associated components.
    1. Deterministic Models – involving components whose behaviour is completely known.
    2. Stochastic Models – involving components, some of them with a behaviour that could be accounted for using rules of probability.

    Models by Time Factor:
    Models are also generally classified into two in terms of the use of time factor as a component or not.
    1. Static models – consider situations with out variation in time factor.
    2. Dynamic Models – are those with ‘time’ being considered either explicitly or implicitly in their construction.

    Models by Method of Solution:
    Models can also be classified according to the nature of solution. There are models whose solution might be obtained using analytical methods. Also, there are models which defy such solutions.
    1. Analytical Models – which subscribe to analytical solutions
    2. Simulation Models – Where solution can be obtained using simulation techniques.

    These models are to be taken not as separate classifications but as possible ways in which a model may have to be comprehended. For instance, there may an abstract model which is dynamic and generated for predictive purposes and containing stochastic components giving possibilities for analytical solutions. The point to be noted is that the generic meaning of “Model” may not be enough to contain all information associated with the problem of study.

    Logical Sequencing of Research:
    With these points included, a further effort is made to make it known a research activity in a step by step way along with a brief explanation about the involved elements. While no distinction is made between qualitative (Substantive) and quantitative research the idea will be more weighted to quantitative methods. Quantitative methods have come to stay as an accepted research method with the computer scenario offering unimaginable facilities. In fact the title of this discussion is to be more directed towards the current scenario in Social science Research Methods rather than their acceptability in philosophical terms.
    Social Science Research provides wide scope for newer technology, especially in gathering and managing data and data analysis, in an unimaginable way. While earlier psychologists spent months for completing a ‘factor analysis’ earlier sociologists used to spend much of their time in validating their instrument using Reliability and other such analyses. Imagine that these techniques require no time at present; they are available for the click of a button. A systematic description of the requirements for good research will be very useful.

    Research process:
    The research process starts with the research worker defining the topic of research and setting their goals. This is followed by a description of ‘Objectives’ which are expected to provide information on these goals in an objective way, so that there will not be any matter of misunderstanding.

    The whole research project starts with
    1. A problem
    2. Setting goals and objectives
    3. Generating appropriate hypotheses.

    Deliberating on these points is highly required to understand the meaning of Research Methodology and to acquire knowledge about them.

    Proposition: It is a statement about observable phenomena that may be judged as true or false.
    Hypothesis: It is ‘A statement that stands to be validated’.

    Research sets a goal with specific objectives and this goal directed by objectives turns out to be good if the associated hypotheses are formulated well.

    Well-framed hypothesis means:
    1. It should guide the direction of the study.
    2. It identifies facts that are relevant and that are not.
    3. It suggests the suitable form of research design
    4. It (they) should be framed in such a way to organize the conclusions that emerge.
    Let us take a simple example from a social problem. Assume that the research problem is about purchase decision in household environment.

    There are many problems here
    Purchase of a house
    Purchase of furniture
    Purchase of HH goods
    Purchase of consumer goods
    Now, what is the most important question related to the Research Problem? “Who is the decision maker?” is the problem. In a HH, generally husband/wife make decisions. Hence, we may formulate hypothesis as “Husband and wife together take purchase decisions in a HH”. Look at the following, “Husband takes decisions about large scale purchases”, “Furniture is bought independently by husband and wife”, “Wife purchases monthly requirements” and others. It is to be noted that none of these individually answers the research problem.

    So where to start? The leading hypothesis, “Husband and wife together take purchase decisions”. Consider “taking purchase decision”. There are three stages here, perception, decision, and execution.

    Can we say?
    a) Husband and wife agree in their perceptions of their respective roles in purchase decisions;
    b) Husband and wife take decisions on mutual agreement;
    c) Purchases are made by husband and wife independently and the likes.
    We see that this process offers wide scope for expansion. For instance, item a) can have its own classification with respect to items, time, value etc. At the end of it, there will be a class of statements that form the basis of study. Some of these statements will be rejected and some of them accepted. Hence, the final outcome will be based on a balance among the findings.

    Problems in Social Science Research will be, generally, related to some “Events”, “Objects”, “Properties”, “Activities”. A major problem is non availability of a common ground for these things. A new term is introduced, i.e. “Concept”.

    By “Concept” we mean a generally accepted collection of meanings/ characteristics Associated with Events, Objects, Properties, Activities
    Look at the following statements

    1. The visitors happened to be both males and females
    2. Students perform at good, average and low levels
    3. A person is walking, running, sitting, crawling.
    4. Market is bullish, bearish, and choppy

    Notice that the statements lead to

    1. The concept of gender
    2. The concept of Student Performance
    3. The concept of Status of a person observed
    4. The concept of Market Behaviour

    Research Problems may lead to concepts which may be in common use i.e., used in normal language like Height, weight, P/E etc. These may not be sufficient and other concepts like Attitude, Model, Satisfaction, Anxiety and others are unavoidable in Research related to Social Sciences.

    Research whether quantitative or substantive, has to address to the question of measurement and comprehension of the concepts respectively. In quantitative research methods there is a wide class of techniques of measurement of concepts. Quantitative methods use these techniques to measure the related concepts and use them under a data analytic framework to validate the hypotheses. Substantive methods should address to the use of logic in going from one statement to another without prejudice to the comprehension of the concepts.

    Measurement in research consists in assigning numbers to empirical events, objects, properties or activities in compliance with a set of rules. This has three stages.
    1. Identification of observable events
    2. Develop a set of mapping rules (A scheme for assigning numbers or symbols)
    3. Apply mapping rules to each case
    Regarding the Mapping Rules of Measurement there are four possibilities.
    1. Classification – Numbers used to group responses, resulting in Nominal Scale.
    2. Order – Numbers used for relative position, resulting in Ordinal Scale.
    3. Distance – Numbers used will have the property that the difference between such numbers can be ordered, resulting in Interval Scale
    4. Origin – Numbers used have a unique origin, resulting in Ratio Scale.

    Characteristics of Good Measurement
    Validity -Extent to which a test measures what is to be measured
    Reliability -Accuracy & precision of the measurement process
    Practicability -Convenience, economy and interpretability

    Validity may be classified into “Internal Validity” and “External Validity”
    Internal Validity refers to the ability of a research instrument to measure what is to be measured.
    External Validity refers to the ability of the method to be generalized across persons, settings and timings.

    Internal Validity has three requirements. They are “Content Validity”, “Criterion Validity” and “Construct Validity”.
    Content Validity refers to the extent to which it provides adequate overage of investigative Concept.
    Criterion Validity reflects the success of measures used for prediction or estimation as the case may be.
    Construct Validity refers to the extent of coherence between theory and measurement.

    Reliability of a measurement is through its consistency. Reliability and validity are connected in the sense that reliability is necessary for validity but not sufficient. There are three requirements for reliability. They are “Stability”, “Equivalence” and “Internal Consistency”.

    Stability refers to using the instrument resulting in the same measurement when an object is measured repeatedly.
    Equivalence relates to the error that may be introduced by different investigators or samples.
    Internal Consistency refers to the degree to which instrument items are homogeneous in reflecting the underlying construct.

    Practicability has three requirements.
    Economy refers to a trade off between ideal and budget.
    Convenience refers to capability for easy implementation.
    Interpretability refers to capability of interpretations when used.

    Descriptive Hypothesis refers to statements about existence, size, form or distribution of some concept (Variable for convenience). Such hypotheses help one to provide answers to direct questions.

     What is the market share for a product?
     Is there any difficulty in accounting in a department?
     What is the expectation of shareholders regarding dividend?
     Do qualified engineers prefer call centre jobs?

    Relational Hypothesis refers to statements that describe a relationship among concepts.
    • Standard of living in Kerala is considered to be better than other states in India.

    Relation may mean
    • Variables have some predictable relation
    • One variable is responsible for changes in other variable

    The first one is Correlational hypothesis and the second one is explanatory hypothesis.

    Correlational Hypothesis refers to a set of broader ‘Relational Hypothesis’ where there is no specification to the first and second. The variables occur in some specified manner.
    “Young women buy fewer greeting cards than aged women”
    Explanatory Hypothesis refers to statements about consequence of change in one variable. There is an implication that a change in one variable causes a change in other variable.
    “An increase in income leads to increase in savings”

    Research and Statistical Methods:
    Quantitative methods are increasingly used in decision making. Even though these techniques are called quantitative techniques, mainly they comprise ‘Statistical Methods’. There is perhaps an unintended importance in the use of the term ‘Quantitative’ instead of ‘Statistics’ here. These points need more considerations in detail. In simple language, the primary purpose of these techniques is to intelligently guess i.e. make probability statements about some problem associated with a collection or group of items by observing only a part of that collection. In a better language, the purpose is to guess from samples in a ‘Scientific’ way so as to make it an intelligent guess.

    This is a small write up.


    Sir, you gave me insight and i want to thank you because now I have a clue. It was very difficult for me to understand how research is done but you were very clear. I heard that when you doing research, journals are so important than textbooks, how true is that? and do textbooks weigh more than other textbooks, if so how do you know that a particular textbook have enough weight that you can consider using it?


    I realy took notes and I am so confident that I am going to do this.


    Dear Friend
    Thanks. In research, generally, we can not relatively assess the importance of Journals and Books. Among books, there may be some which are prescribed for a course and it depends upon the Institution. It may be difficult to point out a particular book as important. I hope we are referring to books on Research Methodology. Choice of books will depend upon the topic of interest. May be difficult to give a general answer. However, if there is some requirement about a book, it may be possible to say if it is okay for a topic of interest. In either case, whether a book or journal, one needs to spend some time very patiently and acquire appropriate information for the requirement of research. Say, in a week, make it a habbit to read at least two articles and make a small note about the topic of the paper, a brief description of the content and a suggestion on the methodology used. All these efforts, in my opinion, must be mannual where one goes through a process of understanding the material read and internalizing the same. The modern gadgets are detrimental to this process because a xerox copy or internet download creates only a feeling of understanding which is virtual. The real understanding takes place only if you make a mannual effort. THIS is my OPINION. Do it for both books and journals. Evaluate what I have said above is true or not after some time. Hope this helps you.

Viewing 12 posts - 1 through 12 (of 12 total)
  • The forum ‘Default Forum’ is closed to new topics and replies.