Topic 8 questionnaire design
Download as PPT, PDF•1 like•1,043 views
The document discusses various aspects of research including types of research studies, styles of research, characteristics of good research, the research process, framing research, designing research, and reporting research. It provides examples and definitions for key research concepts such as problem statements, literature reviews, research question hierarchies, theoretical frameworks, hypothesis generation, research design, measurement, scaling, and data collection.
Topic 8 questionnaire design
- 1. 03/17/1503/17/15 RESEARCH INRESEARCH IN INFORMATIONINFORMATION SYSTEMSSYSTEMS MANAGEMENTMANAGEMENT (IMS 603)(IMS 603)
- 2. 03/17/1503/17/15 Why Do Research?Why Do Research? Research provides you with theResearch provides you with the knowledge and skills needed for the fast-knowledge and skills needed for the fast- paced decision-making environmentpaced decision-making environment
- 3. 03/17/1503/17/15 Types of Research StudiesTypes of Research Studies ReportingReporting DescriptiveDescriptive ExplanatoryExplanatory PredictivePredictive
- 4. 03/17/1503/17/15 Styles of ResearchStyles of Research Applied ResearchApplied Research Pure Research/Basic ResearchPure Research/Basic Research Business ResearchBusiness Research
- 5. 03/17/1503/17/15 What is Good Research?What is Good Research? Purpose clearly definedPurpose clearly defined Research process detailedResearch process detailed Research design thoroughly plannedResearch design thoroughly planned High ethical standards appliedHigh ethical standards applied Limitations frankly revealedLimitations frankly revealed
- 6. 03/17/1503/17/15 What is Good Research (cont.)What is Good Research (cont.) Adequate analysis for decision-Adequate analysis for decision- maker’s needsmaker’s needs Findings presented unambiguouslyFindings presented unambiguously Research design thoroughly plannedResearch design thoroughly planned Conclusions justifiedConclusions justified Limitations frankly revealedLimitations frankly revealed
- 7. 03/17/1503/17/15 The ResearchThe Research ProcessProcessOBSERVATION Broad Area of Research Interest PROBLEM DEFINITION Research problem delineated PRELIMINARY DATA GATHERING Interviews & Literature review THEORETICAL FRAMEWORK Variables clearly identified GENERATION OF HYPOTHESES DATA COLLECTION, ANALYSIS & INTERPRETATION DEDUCTION Hypotheses substantiated? Research Questions answered?
- 8. 03/17/1503/17/15 The ResearchThe Research StagesStages Framing your Research Designing your Research Reporting your Research
- 9. 03/17/1503/17/15 Framing yourFraming your ResearchResearch What is your Research Problem? Why is it Important? How is your Research related to the present body of Knowledge? What are your Research Questions? What are various Concepts involved in your Research and how are they interrelated ? What are their Hypothesized Relationships?
- 10. 03/17/1503/17/15 Designing yourDesigning your ResearchResearch What Research Design to use? What Data to Collect? Where to Collect your Data From? How to Analyze your Data? - Survey vs Experiments - Measurement - Sampling Design - Data Collection Techniques - Data Analysis How to Collect your required Data?
- 11. 03/17/1503/17/15 Final Steps in ResearchFinal Steps in Research Data analysisData analysis Reporting the resultsReporting the results - Executive summary- Executive summary Overview of the researchOverview of the research Findings, Implementation strategies forFindings, Implementation strategies for the recommendationsthe recommendations Technical appendixTechnical appendix
- 12. 03/17/1503/17/15 Problem StatementProblem Statement Existing problem that requires solution Specific areas in the organisation requiring improvement Eg. Complaint of harrassment by senior officers E.g When policy about “harassment” exist but genuine complaint still occur Theoretical or conceptual issue that needs tightening up Eg: What is meant by “harrassment” Research questions that basic researcher needs to answer empirically E.g: Impact of “harrassment” on performance
- 13. 03/17/1503/17/15 Literature ReviewLiterature Review Purpose: Gather related information of research areas Why? Avoid “reinventing the wheel” We do not missed out important variables Problem statement can be stated precisely and accurately “Testability” and “replicability” of findings Clearer idea of what are the important variables
- 14. 03/17/1503/17/15 Research Question HierarchyResearch Question Hierarchy Management Dilemma Level 5 Level 4 Level 3 Level 2 Level 1 Measurement Questions Investigative Questions Research Questions Management Questions
- 15. 03/17/1503/17/15 Examples of ProblemExamples of Problem StatementsStatements To what extent the organizational structure and type of information system implemented explain the effectiveness of managerial decision-making? To what extent the SSB has enhances the motivation level of civil servants? Does leadership style influence the number of turnover?
- 16. 03/17/1503/17/15 Theoretical FrameworkTheoretical Framework A conceptual model that depict how YOU relate all the important variables identified in your study. Helps you generate and test the relationships to enhances your understanding of the dynamics of the problem. Consists of variables and relationships between the variables.
- 17. 03/17/1503/17/15 Example of a TheoreticalExample of a Theoretical FrameworkFramework Air traffic violations Communication between cockpit crew Communication between cockpit and air traffic tower Decentralization Crew training Independent variables Dependent Variable
- 18. 03/17/1503/17/15 Example of a TheoreticalExample of a Theoretical FrameworkFramework Air traffic violations Communication between cockpit crew Communication between cockpit and air traffic tower Decentralization Crew training Independent variables Dependent Variable Nervousness Intervening Variable
- 19. 03/17/1503/17/15 Example of a TheoreticalExample of a Theoretical FrameworkFramework Air traffic violations Communication between cockpit crew Communication between cockpit and air traffic tower Decentralization Independent variables Dependent Variable Moderator Variable training
- 20. 03/17/1503/17/15 Hypothesis GenerationHypothesis Generation An hypothesis is a relationship that is assumed based upon logic, between two or more variables in the form that is testable. Format 1: Differences Testing and validating an assumed hypothesis can leads to problem solution. Format 2: If-then
- 21. 03/17/1503/17/15 Examples ofExamples of HypothesesHypotheses If communication among crew is good then the number of air traffic violation will be reduced Good training among crew members will reduced nervousness and subsequently reduces the number of air traffic violations. If the communication among crew members is good then the number of air traffic violations will be reduced provided they had sufficient training.
- 22. 03/17/1503/17/15 Research DesignResearch Design PROBLEMSTATEMENT Purpose of Study •Exploration •Description •Testing Types of Investigation •Relationship •Correlation •Group differences Unit of Analysis •Individual •Dyads •Groups •Organizations Sampling Design •What/Who? •How many? Study Setting •Contrived •Noncontrived Researcher Interference •Minimal •Manipulation / control/ simulate Time Horizon •Cross-sectional •Longitudinal Measurement •Items •Scaling •Categorizing •Coding Data Collection •Observation •Interviews •Physical •Unobstrusive DATAANALYSIS •Feelfordata •Goodnessofdata •Testing
- 23. 03/17/1503/17/15 What data to collect?What data to collect? Issue of measurement:Issue of measurement: Measurement must beMeasurement must be validvalid andand reliablereliable Source:Source: LiteratureLiterature Self-developSelf-develop
- 24. 03/17/1503/17/15 MeasurementMeasurement ““Development of science is nothingDevelopment of science is nothing but the development of measurement”but the development of measurement” ““Whenever you can, count”Whenever you can, count” ““Everything that countsEverything that counts should be counted”should be counted”
- 25. 03/17/1503/17/15 MeasurementsMeasurements Empirical research often implies measurementsEmpirical research often implies measurements Quality of information depends on theQuality of information depends on the measurement processmeasurement process Measurement Defined:Measurement Defined: The mapping of some propertiesThe mapping of some properties Rules for assigning numbers to empirical propertiesRules for assigning numbers to empirical properties Rules: specify the procedure according to whichRules: specify the procedure according to which numbers are to be assigned to objectsnumbers are to be assigned to objects
- 26. 03/17/1503/17/15 Working DefinitionsWorking Definitions MeasurementMeasurement is a process through which theis a process through which the kind or intensity of something is determined: i.e.kind or intensity of something is determined: i.e. measurement ismeasurement is the process of linking abstract concepts to empiricalthe process of linking abstract concepts to empirical indicants.indicants. DimensionalityDimensionality refers to the number of differentrefers to the number of different qualities inherent in a theoretical concept.qualities inherent in a theoretical concept. AA conceptconcept is a general idea referring to ais a general idea referring to a characteristic of an individual, group, or a nation.characteristic of an individual, group, or a nation.
- 27. 03/17/1503/17/15 Working DefinitionsWorking Definitions Example:Example: • The Theoretical Concept:The Theoretical Concept: Social StatusSocial Status • Dimensions:Dimensions: Occupational Prestige,Occupational Prestige, Ethnicity, Popularity, EducationalEthnicity, Popularity, Educational Prestige, Financial Resources, and so on.Prestige, Financial Resources, and so on.
- 28. 03/17/1503/17/15 How are Variables Measured?How are Variables Measured? Objective – precise measurementObjective – precise measurement Subjective – nebulous & abstract; e.g.Subjective – nebulous & abstract; e.g. attitude, beliefs, involvement,attitude, beliefs, involvement, satisfactionsatisfaction Concept ofConcept of “Thirst”“Thirst” Process of reducing abstract concept toProcess of reducing abstract concept to measurable items is calledmeasurable items is called OperationalizationOperationalization
- 29. 03/17/1503/17/15 OperationalizationOperationalization Concept Operational Definition Dimensions A generalized idea about a class of objects, attributes, occurrences, or processes e.g. sex, loyalty Gives meaning to a concept by specifying the activities or operations necessary to measure it Elements Broad characteristics to ensure coverage or scope of the concept Specific items about the identified measurement, which are easily measured
- 30. 03/17/1503/17/15 Operationalizing: LearningOperationalizing: Learning Learning Understanding Retention Application Answer questions correctly Give appropriate examples Recall material after some lapse Solve problems applying concepts understood and recalled Integrate with other relevant material e e e e e d d d
- 31. 03/17/1503/17/15 Operationalizing: MotivationOperationalizing: Motivation Achievement Motivation Driven by work Unable to relax Impatience with ineffectiveness Constantly working Reluctance to take time off e d Seeks moderate challenges Seeks feedback Persist despite setbacks Work at home No hobby Swears at small mistakes Does not like to work with incompetent people Opt for challenging not routine Opt for moderate rather than overwhelming challenge Ask for feedback about job done Wants immediate feedback
- 32. 03/17/1503/17/15 Operational definition isOperational definition is NOTNOT CorrelateCorrelate AntecedentsAntecedents ConsequencesConsequences ReasonsReasons …… of the conceptof the concept
- 33. 03/17/1503/17/15 ScalesScales A tool or mechanism by whichA tool or mechanism by which individuals are distinguished on howindividuals are distinguished on how they differ from one anotherthey differ from one another E.g. how do we distinguish individualE.g. how do we distinguish individual A from B in terms of learning?A from B in terms of learning? Also refers to level of measurementAlso refers to level of measurement
- 34. 03/17/1503/17/15 Levels Of MeasurementsLevels Of Measurements Empirical Scale Basic Operations Measures of Typical use Averages Nominal Determination of equality Classification Male-Female Occupations Mode Ordinal Determination of greater or less Ranking Preference Attitude Median Interval Determination of equality of intervals Index numbers Temperature Mean Ratio Determination of equality of ratios Sales Unit produced No. of customers Mean Geometric
- 35. 03/17/1503/17/15 Nominal ScaleNominal Scale Classificatory or Categorical e.g. Sex – Male/Female Colour Mutually exclusive & collectively exhaustive
- 36. 03/17/1503/17/15 Ordinal ScaleOrdinal Scale Categorize and rank e.g. Preference in job attributes Please rank from 1 most important to 5 least important the following attributes: Interacting with others Using multiple skills Completing a task from beginning to end Serving others Work independently
- 37. 03/17/1503/17/15 Interval ScaleInterval Scale Allows for measurement of distance between two points on the scale e.g. Preference in job attributes Using a scale of 1 (strongly disagree), 2 (disagree), 3 (neither agree nor disagree), 4 (agree) and 5 (strongly agree), please indicate the extent of your agreement by circling the appropriate number. The following are very important to me Interacting with others 1 2 3 4 5 Using multiple skills 1 2 3 4 5 Complete a task from beginning to end 1 2 3 4 5 Serving others 1 2 3 4 5 Working independently 1 2 3 4 5
- 38. 03/17/1503/17/15 Ratio ScaleRatio Scale Has absolute zero; thus allowing for not only differences but also proportions in the differences e.g. Number of years in the organization
- 39. 03/17/1503/17/15 Properties of the 4 ScalesProperties of the 4 Scales Characteristics Difference Order Distance Unique Origin Measure of Center Measure of Dispersion Scale Nominal Ordinal Interval Ratio Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Yes Mode Median Mean Arithmetic &Geometric mean Semi- interquartile range Standard deviation Standard deviation, Coefficient of variation
- 40. 03/17/1503/17/15 Scaling MethodsScaling Methods Rating Scales •Dichotomous Scale •Category Scale •Likert scale •Numerical Scale •Semantic Differential Scale •Itemized rating scale •Graphic rating scale Ranking Scales •Paired Comparison •Forced Choice •Comparative Scale
- 41. 03/17/1503/17/15 Examples: Rating ScaleExamples: Rating Scale Likert Do you own a car Yes NoDichotomous Where do you stay Kedah Penang Perlis Category My work is very interestingMy work is very interesting Strongly agreeStrongly agree AgreeAgree Neither agree nor disagreeNeither agree nor disagree DisagreeDisagree Strongly disagreeStrongly disagree
- 42. 03/17/1503/17/15 Examples: Rating ScaleExamples: Rating Scale How would you rate your work partners Responsive __ __ __ __ __ __ __ Unresponsive Semantic Differential Numerical Rating Scale How please are you with your insurance agent Extremely Extremely Pleased __ __ __ __ __ __ __ displeased Itemized Rating Scale Very netiher unlikely Very Likely likely nor likely unlikely unlikely 1 2 3 4 5 I will be changing my job within the next 3 months __ I will take on new assignment in the near future __
- 43. 03/17/1503/17/15 Examples: Rating ScaleExamples: Rating Scale Graphic Rating Scale On a scale of 1 to 10 how would you rate your supervisor 1 Very bad 5 all right 10 Excellent
- 44. 03/17/1503/17/15 Examples: Ranking ScaleExamples: Ranking Scale When comparing a small number of objects, respondents are asked to choose between two objects at a time Paired Comparison Forced Choice Rank your preferences among the following magazines, which you would like to subscribe to, 1 being the most preferred choice and 4 being the least preferred: Asiaweek __ Economist __ Fortune __ Newsweek __
- 45. 03/17/1503/17/15 Examples: Ranking ScaleExamples: Ranking Scale Comparative Scale In a volatile financial environment, compared to stocks, how wise or useful is it to invest in bonds? Please circle the appropriate response. More usefulMore useful About the sameAbout the same Less usefulLess useful 11 22 33 44 55
- 46. 03/17/1503/17/15 Goodness of MeasuresGoodness of Measures 1. Item Analysis Test whether items in the instruments should belong there. Steps: 1. Calculate Total Score 2. Divide respondents into high and low score 3. Compute t-test for each item 4. Use only items that are significant 2. Reliability Analysis Is the measure without bias (error free) and therefore consistent across time and across items in the instrument? i.e. is it stable and consistent? 3. Validity Analysis Is the instrument measuring the concept it sets out to measure and not something else?
- 47. 03/17/1503/17/15 Goodness of MeasuresGoodness of Measures GOODNESS OF DATA Reliability (Accuracy) Validity (Actuality) Stability Consistency Test-retest Parallel form Interitem consistency Split-half Logical (content) Criterion related Congruent (construct) Face Predictive Concurrent Convergent Discriminant
- 48. 03/17/1503/17/15 Reliability and ValidityReliability and Validity Valid but Unreliable Valid & Reliable Reliable but NOT Valid
- 49. 03/17/1503/17/15 ReliabilityReliability Observed scores may reflect true scores,Observed scores may reflect true scores, but it may reflect other factors as well:but it may reflect other factors as well: stable characteristics: two people having thestable characteristics: two people having the same opinion may circle different responsessame opinion may circle different responses transients personal factors such as moodtransients personal factors such as mood situational factors, time pressure, timesituational factors, time pressure, time variations in administration and mechanicalvariations in administration and mechanical factorsfactors Reliability: Stability and consistencyReliability: Stability and consistency StabilityStability – over time, conditions, state of– over time, conditions, state of respondentsrespondents ConsistencyConsistency – Homogeneity of times; items can– Homogeneity of times; items can measure the construct independentlymeasure the construct independently
- 50. 03/17/1503/17/15 Reliability of MeasuresReliability of Measures RELIABILITY Stability Consistency Test-retest Parallel form Repeated measures on the same respondent; high correlation – high reliability Two comparable sets of measures for the same construct; same items, same response format but different wording; Analysis - correlation Interitem Split-half Consistency of respondents’ answer to all the items; high correlation among responses to the items – Cronbach α Correlation between two- halves of a measure; correlation between the two halves
- 51. 03/17/1503/17/15 ValidityValidity Multiple indicators: - often used to capture aMultiple indicators: - often used to capture a given construct e.g. attitude; togiven construct e.g. attitude; to cover the domain of the constructcover the domain of the construct robust - reduce random errorrobust - reduce random error Cronbach alpha - measures intercorrelationCronbach alpha - measures intercorrelation between indicators - they should be positivelybetween indicators - they should be positively correlated but not perfectly correlatedcorrelated but not perfectly correlated Construct ValidityConstruct Validity Face validityFace validity Convergent validity (Correlation to assess it)Convergent validity (Correlation to assess it) Divergent validityDivergent validity
- 52. 03/17/1503/17/15 ValidityValidity VALIDITY Logical (content) Criterion related Congruent (construct) Face Ensures adequate and representative set of items that tap the concept Panel of judges – face validity Predictive Concurrent Does measure differentiate to predict a future criterion variable Analysis – Correlation Does measure differentiate to predict a criterion variable currently Analysis – Correlation Convergent Discriminant Do the two instruments measuring the concept correlate highly? Does the measure have low correlation with an unrelated variable?
- 53. 03/17/1503/17/15 Data Source: SamplingData Source: Sampling Two Central QuestionsTwo Central Questions Do weDo we samplesample oror censuscensus?? If sample:If sample: How to identifyHow to identify Who/whatWho/what to include into include in the sample? - sampling designthe sample? - sampling design HowHow manymany to include in the sample? -to include in the sample? - sample sizesample size
- 54. 03/17/1503/17/15 What is a Good Sample?What is a Good Sample? RepresentativeRepresentative of the Populationof the Population Estimates from sample areEstimates from sample are accurateaccurate Estimates from sample areEstimates from sample are preciseprecise
- 55. 03/17/1503/17/15 Steps in Sampling DesignSteps in Sampling Design What is the relevantWhat is the relevant populationpopulation?? What are theWhat are the parametersparameters of interest?of interest? What is theWhat is the sampling framesampling frame?? WhatWhat sizesize sample is needed?sample is needed? What is theWhat is the typetype of sample?of sample? How much will itHow much will it costcost??
- 56. 03/17/1503/17/15 Types of SamplingTypes of Sampling DesignDesign Non- probability Design Probability Design Convenience Judgement Quota Snowball Simple Random Systematic Stratified Cluster Simple Random Stratified Combination Sampling Design One-stage design Multistage design
- 57. 03/17/1503/17/15 Choosing a SamplingChoosing a Sampling DesignDesign Is REPRESENTATIVENESS critical? Area samples Only experts have information Info from special interest groups QuotaJudgement Quick, unreliable information Relevant information about certain groups Convenience Simple random Systematic Cluster if not enough RM Double samples Equal sized subgroups? Proportionate stratified samples Disproportionate stratified samples YES NO Choose PROBABILITY design Choose NON-PROBABILITY design NOYES Generaliza bility Subgroup Differences Collect localized information Information about subsets of sample
- 58. 03/17/1503/17/15 Sample Size: FactorsSample Size: Factors HomogeneityHomogeneity of sampling unitsof sampling units ConfidenceConfidence levellevel PrecisionPrecision Analytical ProcedureAnalytical Procedure Cost, Time and PersonnelCost, Time and Personnel
- 59. 03/17/1503/17/15 Roscoe’s Rule of ThumbRoscoe’s Rule of Thumb Larger than 30 and less than 500Larger than 30 and less than 500 appropriate for most researchappropriate for most research A minimum of 30 for each sub samplesA minimum of 30 for each sub samples Multivariate research: At least 10 timesMultivariate research: At least 10 times the number of variablesthe number of variables Simple Experiments with tight controlsSimple Experiments with tight controls - samples as small as 10 to 20- samples as small as 10 to 20
- 60. 03/17/1503/17/15 Types of Primary DataTypes of Primary Data Collection MethodCollection Method Data Collection Method Passive Active Disguised/ Undisguised Structured/ Unstructured Human/ Mechanical Disguised/ Undisguised Structured/ Unstructured •Personal •Telephone •Mail •Mechanical
- 61. 03/17/1503/17/15 Personal InterviewPersonal Interview Major concerns:Major concerns: Non-responseNon-response Response errorsResponse errors Non-responseNon-response Call-back, prior introduction, specific timesCall-back, prior introduction, specific times Response BiasResponse Bias Interview variations (situations, interviewer)Interview variations (situations, interviewer) Question structuring & sequence (protocol)Question structuring & sequence (protocol) Method of administration (socially accepted)Method of administration (socially accepted) Respondent error (intentional and unintentional)Respondent error (intentional and unintentional)
- 62. 03/17/1503/17/15 The InterviewThe Interview IntroductionIntroduction Establishes rapportEstablishes rapport Gather DataGather Data Probing (brief assertion of understanding,Probing (brief assertion of understanding, expectant pause, repeating the question,expectant pause, repeating the question, repeating the answer, neutral comment,repeating the answer, neutral comment, question clarification)question clarification) Recording the InterviewRecording the Interview
- 63. 03/17/1503/17/15 Self-Administered SurveySelf-Administered Survey TypeType Intercept StudyIntercept Study Mail surveyMail survey DisadvantagesDisadvantages Large non-response errorLarge non-response error Superficial dataSuperficial data Improving Response RateImproving Response Rate Reduced length; survey sponsorship, return envelope,Reduced length; survey sponsorship, return envelope, return postage, personalization, anonymity, size colorreturn postage, personalization, anonymity, size color and reproduction, deadline dates, cover lettersand reproduction, deadline dates, cover letters
- 64. 03/17/1503/17/15 Data Analysis – The StagesData Analysis – The Stages InterpretationInterpretation PreanalyticalPreanalytical •Data Editing •Variable Development •Data Coding •Error Check Data AnalysisData Analysis •Feel for Data •Goodness of Measures •Inferential: Testing & Relationships
- 65. 03/17/1503/17/15 Data Analysis - TypesData Analysis - Types Number of VariablesNumber of Variables Univariate; Bivariate; MultivariateUnivariate; Bivariate; Multivariate Level of MeasurementsLevel of Measurements Nominal, Ordinal, Interval & RatioNominal, Ordinal, Interval & Ratio Purpose of StudyPurpose of Study Exploratory; Test of Differences;Exploratory; Test of Differences; Establishing RelationshipsEstablishing Relationships
- 66. 03/17/1503/17/15 The Right Technique?The Right Technique? Number of VariablesNumber of Variables Univariate; Bivariate; MultivariateUnivariate; Bivariate; Multivariate Level of MeasurementsLevel of Measurements Parametric and Non-parametricParametric and Non-parametric Research QuestionResearch Question Concern for Central Tendency;Concern for Central Tendency; Comparing groups; RelationshipsComparing groups; Relationships
- 67. 03/17/1503/17/15 The Right Technique?The Right Technique? What is the purpose of the analysis?What is the purpose of the analysis? What is the level of measurement?What is the level of measurement? How many variables are involved?How many variables are involved?
- 68. 03/17/1503/17/15 Descriptive AnalysisDescriptive Analysis TechniquesTechniques Frequencies Distribution - if 1 ordinal orFrequencies Distribution - if 1 ordinal or nominal variable,nominal variable, Cross-tabulation - if 2 ordinal or nominalCross-tabulation - if 2 ordinal or nominal variablesvariables Means - if 1 interval or ratio level variableMeans - if 1 interval or ratio level variable Means of subgroups - if 1 interval or ratioMeans of subgroups - if 1 interval or ratio level variable by subgroupslevel variable by subgroups PurposePurpose:: To describe the distribution of theTo describe the distribution of the variables of interestvariables of interest
- 69. 03/17/1503/17/15 Test of DifferencesTest of Differences TechniquesTechniques depends ondepends on Levels of Measurement of the VariableLevels of Measurement of the Variable Number of GroupsNumber of Groups Independence of the GroupsIndependence of the Groups PurposePurpose:: To evaluate the differencesTo evaluate the differences between 2 or more groups with respect to abetween 2 or more groups with respect to a variable of interestvariable of interest
- 70. 03/17/1503/17/15 Test of DifferencesTest of Differences More than 2 group? Are they independent ? Are they independent ? Nominal: χ2- test Ordinal: Mann-Whitney Continuous: t- test Yes Nominal: McNemar Ordinal: Wilcoxon Signed Rank Continuous:- Paired t-test No No Yes Nominal: χ2 test Ordinal: Kruskal- Wallis ANOVA Continuous: 1-way ANOVA Nominal: χ2 - test Ordinal: Friedman 2-way ANOVA Continuous: Factorial 2-way ANOVA
- 71. 03/17/1503/17/15 RelationshipRelationship TechniquesTechniques depends ondepends on Whether or not there exist dependentWhether or not there exist dependent variable(s)variable(s) Number of dependent and independentNumber of dependent and independent variablesvariables Levels of Measurement of the VariableLevels of Measurement of the Variable PurposePurpose:: To establish relationshipTo establish relationship between variablesbetween variables
- 72. 03/17/1503/17/15 DependenceDependence RelationshipsRelationshipsHow many dependent variables? Scale of Dependent Multiple Regression ANOVA Discriminant Analysis Canonical Correlation Scale of Independe nt Scale of Dependent Scale of Independen t Multivariate ANOVA More than 1 One Conjoint Analysis Scale of independen t Interval Nominal Interval Nominal Scale of Independe nt Interval Nominal Interval
- 73. 03/17/1503/17/15 Contents of a ResearchContents of a Research ProposalProposal Data preparationData preparation A brief description of researchA brief description of research methodologymethodology Data collectionData collection Data analysis and interpretationData analysis and interpretation Research reportingResearch reporting A statement of the research problemA statement of the research problem
- 74. 03/17/1503/17/15 Final WordsFinal Words Good Luck in Your Research and Remember the Good Research begins with an Inquisitive Mind