RESEARCH METHODOLOGY

RESEARCH METHODOLOGYMEANING, PURPOSE of ResearchUsually regarded as a serious academic activityA systematic activity with a set of objectives to find a solution to a problem(s)Sometimes referred to as manipulation of things, concepts, or symbols for the purpose of generalising to extend verify or correct knowledge to either add to theory or aid practicePurpose.Understand a particular phenomenaTo reveal characteristics of an individual/ group/situationTo test a hypothesis about the casual relationship between two variables

Theory and ResearchTheory refers to isolated facts whereas research refers to logical interlinking of these facts to arrive at a conclusion or a solutionResearch should ideally aid in understanding the problem and offering solution Social research deals with problems of groups of human beingsA general pattern is found which makes a reasonable prediction possibleApproaches to research Historical approach- past data is collected and analyzed to yield results.Descriptive approach- suitable for empirical problemsCase study approach- A particular unit of study is chosen for an in depth analysisExperimental approach- a scientific approach using factors affecting a problem-called variables

Techniques in defining the research problemStatement of problem in a broad mannerUnderstand origin and nature of the problemSurvey of available literatureDeveloping the ideas through discussionRephrasing the research problemResearch design-to consider the following:Means of obtaining informationAvailability of skilled researchersObjectives /problem- NatureAvailability of time and moneyConcepts relevant to Research design

Dependent and independent variableExtraneous variableControl Confounded relationshipResearch hypothesisExperimental and non experimental hypothesis testing researchExperimental and control groupsTreatments Developing a research planAfter identifying and defining the problem, the researcher should arrange his ideas in order and write them in the form of an experimental plan.This is to organise ideas to spot any flawsIt provides an inventory of materials to be collectedCan be vetted by experts for comment and improvementsResearch plan to contain:Clear objectives in a line or twoProblems to be explicitly statedConcepts to be defined in operational contextOverall approach and assumptions if anyDetails of techniques of data collection/ instruments to be used etc.Clearly mention population and sampling planMethods for processing of data to be used tooResults of pilot studies to be documentedTime and cost budget to be laid downSampling designUniverse or PopulationCensus and Sample survey

How a sample is chosen from a polpulation is called sampling technique.The sampling technique is decided upon after due deliberation.Sample size and technique make up sampling design- it should be appropriate and reliable to the proposed studySteps in sampling designType of universe. Based on objectivesSampling unitSampling frame/source listSize of sample- very crucial decisionParameters of interestBudgetary constraintsSampling procedure

Characteristics of a good sample designShould yield a truly representativeShould result in a relatively small sampling errorViable in the context of funds availableSystematic bias can be controlledResults of study should be applicable to the universeDifferent types of sample designsProbability sampling- simple random sampling and Complex random sampling such as cluster, area, multi stage,systematic, stratified etc.How are strata formed? How should items be selected from each stratum and how many?Non probability sampling such as haphazard or convenience sampling& purposive sampling such as quota or judgment samplingMEASUREMENT AND SCALING TECHNIQUESMEASUREMENT IN RESEARCH- what it meansWhat yardsticks are used??Weight, age, income,marks, etc. are quantifiableWhat about liking, motivation, stress, success of a policy changeAbstract aspects are not easily measurable.Measurement scalesNominal scaleOrdinal scaleInterval scaleRatio scaleTechnique of developing measurement toolsConcept developmentSpecification of concept developmentSelection of indicatorsFormation of indexSources of error in measurementRespondent Situation Measurer Instrument To test positive for Validity, Reliability and PracticalityTESTS OF SOUND MEASUREMENTTest of validity: content, criterion related and construct validityReliability: stability and equivalencePracticality : economy, interpretability and convenience

Scaling Scaling describes the procedures of assigning numbers to various degrees of opinion, attitude and other concepts

Scale classification basesSubject orientationResponse formDegree of subjectivityScale propertiesNumber of dimensionsScale construction techniques arbitrary approach, consensus approach, cumulative scales, factor scalesImportant scaling techniquesRating scales: like, dislike, above average, below average etc.graphic rating scale: a continuum with a five point scale; like very much, like, neutral, dislike, dislike v much etc.itemized rating scale: a numerical scale where a set of probable answers are arranged and respondent asked to select one and points are allottedRanking scales relative judgments against similar objects.

TYPES OF SCALESArbitrary scales: designed on subjective selection of items by researcher; totally dependent on researchers competenceDifferential scales (Thurston type): selection of items made by a panel of judges- here large number of statements to express points of view towards particular idea- each judge arranges it in order-median scale value is assigned for each item-then an order is created as final scaleSummated scales (Likert type scales)Summated scales consist of a series of statements which express a favourable or unfavourable attitude / agreement or disagreement.Each response is given a score. Scores are totaled to measure the attitude/ success/ agreement/ performance or any such non measurable conceptCumulative scalesThis method consists of a series of statementsThe statements are all related to one another and measures an individuals attitude by different statements by allotting scoresA favorable response to one usually indicates so for the rest too.A scalogram is then constructed to determine a patternFactor scalesThis scale is developed on basis of inter correaltions of items which indicate common factors for relationshipsThis is very useful in uncovering latent attitude dimensionsThis method is multi dimensional in approachIt could use a semantic differential scale or Multidimensional scaling techniqueThis method measures both direction and intensity and is very popular in social researchSteps in S D scaleAll concepts to be studied are developedSelect scales bearing the criterion in mind. Bipolar rating is used; for eg: like-dislike, strict-lenient,active-passive,sociable-unsociable.A panel of judges are used to rate various stimuli on selected scales and responses of all judges are combines to get a composite scalingSOURCES OF Data collectionPrimary and secondary dataPrimary data are those collected for first time and are original/raw in natureSecondary data refers to data collected and processed by another researcher/ writer/study groups etc.Methods of data collection differ as first involves collection from source/respondents whereas the second on is better known as compilation Collection of primary dataMainly used in experiments and surveysCan use observation or direct communicationObservation method is mostly used for study of behavioural sciences- its to be systematically planned and checked for reliability and validity- can be structured or unstructured may be participant or non participant observer/disguised observation- controlled/uncontrolled observationInterview method :Interview method of collecting by creating oral/ verbal stimuli and responsesCategories- Personal interviews- direct /indirect may be structured or unstructured- maybe focused/clinical or non directive interviews Interview method is most preferred form of primary data collection especially in exploratory studies, but its chief demerit is that its expensive.Basic tenets of interviewingIts an art governed by scientific principlesInterviewers must be carefully selected, trained and briefedThey must be persons of integrity and impartial and possess technical competenceA provision be created in case respondents refuse to cooperate or are unavailableAn interviewer should be non committal when respondent replies or states opinionsTelephonic interviewsMeans of collecting information through telephoneVery useful for industrial surveys in developed regionsFlexible and faster than mailed interviewsnot suitable for intensive surveysGeographical limits can be overcome by this methodCOLLECTION OF DATA THROUGH QUESTIONNAIRESList of questions printed in order and sent/given to respondentThe respondent has to interpret and understand and answer in space provided or tick relevant boxEspecially suitable where universe is large and spread wide geographicallyEducated respondents are requiredCooperation of respondent is essential for success of questionnaire methodKey issues in questionnaire buildingGeneral form: structured or unstructuredOpen ended or close endedPilot study/survey- unstructured questionnaire may be used in pilot studies and responses used to form a structured oneQuestion sequence-to be clear, smooth moving and meaningful; first few questions are most significant. Question formulation/ wording/ grouping-Essentials of a good questionnaireShould be relatively simple and shortShould proceed in a logical sequencePersonal and intimate questions should be to the endTechnical terms to be minimumAdequate space for answersTips to help respondentsCatch phrases with personal connotations to be avoidedShould facilitate compilation and analysis

Collection of data through schedulesSimilar to questionnaire method but answers are filled by enumeratorThe surveyor/ enumerator explains the objective of the research and elicits answers/ responses which he himself records in respective space.The enumerators have to be properly trained/ and should know the subject of research well, should be honest and have perseverance Other methods of data collectionWarranty cardsDistribution/stores auditPantry auditsCustomer panelsUse of mechanical devicesProjective techniques -word association tests,sentence completion tests, pictorial tecniques, play techniques,quizzes,Depth interviewsContent analysisCollection of secondary dataInformation available in various published records such as:

Central /state/ local government records publications and journals, newslettersBooks/magazines/newspapersAssociation of trade, commerce etc.- Reports /surveys/reportsBusiness houses and stock exchanges

Unpublished data may be referred too like diaries, autobiographies, letters, notes taken etc. However Reliability, suitability and adequacy must be considered before choosing a secondary source

Experimental research Experimental research is a systematic and logical method to find the outcome and measure the change when a set of variables are controlled/manipulated. These are mostly laboratory research and relate to physical /natural sciences. A problem is defined and hypothesis framed. Then testing of hypothesis is done to confirm or rejectThe research design must be such that it reduces bias and permit inferences about casuality

Case study methodThis is a method by which an individual factor whether it be an institution or just an episode in the life of an individual or group is analyzed in its relationship to any other in the group.Also referred to as the social microscopeA single unit is chosen and an in-depth study is done. The study extends over a long period of time to draw inferences.It is a widely used method of field research in sociology studies. Processing of informationData after collection has to be processed and analysed in accordance to the research design/planProcessing implies editing, coding, classification and tabulation of collected dataAnalysis is possible when tabulated data can be tested for relationshipsHypotheses can be tested for significance based on aboveThere are few researchers who do not differentiate between processing and analysisEditing

Editing of data is a process of examining collected raw data to detect errors of omission and commission and to correct them if possible.Field editing consists of review of investigating officers reportsCentral editing consists of a thorough editing by a centralized editing team.Editors should be well trained and familiar with the instructions supplied to investigators

Coding Coding refers to the process of assigning numerals or other symbols to answers/ responses They must be exhaustive; ie no class/category must be left uncodedCoding is very necessary to give clarity to a mass of dataCoding helps to transcribe data from questionnaireClassification of Data and TabulationLarge volumes of data reduced to homogenous groups to get meaningful relationships classification may be done according to attributes or by creating class intervalsA logical order of arranging information in tables is referred to as tabulationAccepted principles of tabulation state that tables should have titles, number/codes, adequate captions, footnotes, references, and not too many columns/rowsTesting of HypothesisIt is a principal instrument in researchMany experiments are carried out specifically to test out hypothesesIn social sciences where awareness of parameters of a population is not common, a sample drawn and tested for hypotheses helps to make generalisations

What is a hypothesis; its characteristicsA research hypothesis is a predictive statement capable of being tested for validityFor eg: students who receive coaching write betterFor eg: Factory A is performing as well as Factory BCHARACTERISTICS: clear and precise; capable of being tested, should be relational, consistent with a known body of facts, one should be able to deduce the problem from the empirical referencesBasic concepts of hypothesesNull and alternative hypothesesLevel of significanceDecision rule or tests of hypothesisType I and Type II errorsTwo tailed and one tailed testsReport WritingWriting a research report A research report can be based on practical work, research by reading or a study of an organisation or industrial/workplace situation.1.Preparing

Identify the purpose/the aims of the research/research question.Identify the audience. lecturer/supervisor/company/organization management/staff. The amount of background included will vary depending on the knowledge of the audience.

Organising Collecting and organising information There are two main sources of information depending on the research task:1. Reading theory and other research2. Research experiments, data collectionquestionnaires, surveys, observation, interviewsOrganise and plan Organize and collate the information in a logical order. Make sure you record the bibliographic information of your reading as you go along.(See Quick Tips on mind mapping techniques)3. Planning Before writing the report, prepare a detailed plan in outline form.Logical organisation

Information in a report must be organized logically. Communicate the main ideas followed by supporting details and examples. Start with the more important or significant information and move on to the least important information.Headings Use headings and suitable sub headings to clearly show the different sections. In longer reports the sections should be numbered.4. Writing the Report

1. Draft the report from your detailed plan.2. Do not worry too much about the final form and language, but rather on presenting the ideas coherently and logically.3. Redraft and edit. Check that sections contain the required information and use suitable headings, check ideas flow in a logical order and remove any unnecessary information.4. Write in an academic style and tone.Academic reporting style Use a formal objective style.

Generally avoid personal pronouns; however, some reports based on your own field experience or work placement can be reflective the first person can be used. For example, I observed... If in doubt about this, check with the faculty guide

Writing a research report Section- Purpose Title page- Title of report ;Student name/student number ;Course/subject ;Date due Table of contents - Shows the sections of the report Executive summary -Gives a summary of the whole report; outlines -purpose, research method, findings, the main conclusions and recommendations; written mainly in past tense; written last sections of a research report Introduction /methodologyOutlines context, background and purpose Defines terms and sets limits of the research The reader/audience can easily identify what, how, why (Mainly uses past tense and can be written later although presented first) Methodology- Explains how research was done and outlines how the data was collectedResults/FindingsThe above may be combined Presents findings of the research Facts only - no interpretation Uses graphic form (eg. tables & graphs) Discussion. Discussion Presents an interpretation and evaluation of the results. Analyses results - draws together different aspects of the findings, findings of other studies and refers to literature Conclusion & recommendations Conclusion and recommendations/suggestions may be combined Brief statement of what was found Recommendations - Suggest suitable changes/solutions based on your findings of studyAppendixAppendix- Attachments of additional information (eg. surveys, questionnaires, glossary etc) References - All references used in report

NB: Further headings and subheadings are content based and are particular to the individual report.How to Write a Research Report and Give a Presentation Things to Remember When Starting A Presentation Start with something to get your audiences attention. Tell your audience what your argument will be. Tell your audience how you are going to develop that argument. Presentation Outline: Writing a Research Report

Getting started and planning Sections of a typical report Presentation of text, maps, and illustrations Referencing Presenting Your Research Strategies for presentation Designing visuals for your presentation Presenting Your Research :General Tips

Speak slowly and clearly Dont fidget Dont stand still like a statue Use a podium to hold your notes Set a stop watch to gauge time Designing Presentation Graphics Graphics should be visible from far away Serif fonts are easier to read than Sans-Serif Fonts Make sure your text contrasts with your background Make sure your maps and illustrations are of professional quality Do not expect people to read stuff off the screen--read it for them Do not show large tables of data. Provide a hand out or create a summary table with relevant results highlighted.

Contd.Do not use too many slides Keep information on slides to a minimumIf you want your audience to listen to you insert a blank slide Use large printMore than four lines of text are hard to read on a screen.How to end a presentationHave ready a list of FAQ sSave some time for questionsBe ready to go to research objectives/ research design / findings as and when requiredBe gracious in accepting shortcomings of your research