36
Lecture 2 Lecture 2 Research Questions: Research Questions: Defining and Justifying Defining and Justifying Problems; Defining Problems; Defining Hypotheses Hypotheses

Lecture 2 Research Questions: Defining and Justifying Problems; Defining Hypotheses

  • View
    221

  • Download
    0

Embed Size (px)

Citation preview

Lecture 2 Lecture 2

Research Questions: Defining and Research Questions: Defining and Justifying Problems; Defining Justifying Problems; Defining

Hypotheses Hypotheses

22

Announcements:Announcements:

SPSS installed on following PC’s:SPSS installed on following PC’s: Upstairs labUpstairs lab

BisqueBisque

CitronCitron

CrimsonCrimson

EbonyEbony

RubyRuby

OliveOlive BasementBasement

LavenderLavender

SiennaSienna

33

Our Focus Today:Our Focus Today:

What makes a good research What makes a good research problemproblem?? Research Questions for Theory DevelopmentResearch Questions for Theory Development Research Questions for Practical ApplicationResearch Questions for Practical Application

Turning research problems into testable Turning research problems into testable hypotheseshypotheses

44

Purpose of ResearchPurpose of Research

To increase knowledge within a discipline To increase knowledge within a discipline or an area of study.or an area of study.

To increase knowledge as a consumer of To increase knowledge as a consumer of research and to understand research research and to understand research within a discipline or area of study.within a discipline or area of study.

55

Increasing Knowledge Within a Increasing Knowledge Within a Discipline or Area of StudyDiscipline or Area of Study

For Theory DevelopmentFor Theory Development

Practical ApplicationPractical Application

Developing Research ToolsDeveloping Research Tools

66

Defining Research ProblemsDefining Research Problems

What is a What is a problemproblem??

““an interrogative sentence or statement that asks: an interrogative sentence or statement that asks: What relation exists between two or more concepts?”What relation exists between two or more concepts?”

A problem can be restated in one or more ways to A problem can be restated in one or more ways to produce testable hypotheses.produce testable hypotheses.

A good research problem often produces more than A good research problem often produces more than one testable hypothesis.one testable hypothesis.

77

Characteristics of good research Characteristics of good research problemsproblems

Should state the concepts or variables to Should state the concepts or variables to be related clearly and unambiguouslybe related clearly and unambiguously

Should be testableShould be testable

Should be feasible, given resourcesShould be feasible, given resources

88

Three Specific Criteria for a Three Specific Criteria for a Research ProblemResearch Problem

What are we going to learn as the result of What are we going to learn as the result of the proposed project that we do not know the proposed project that we do not know now? now?

Why is it worth knowing? Why is it worth knowing?

How will we know that the conclusions are How will we know that the conclusions are valid? valid?

99

The Research QuestionThe Research Question

Common mistakes in defining research Common mistakes in defining research questionsquestions

Very broad area of interestVery broad area of interest Too narrowToo narrow Cannot be measuredCannot be measured Problem is trivial or already understoodProblem is trivial or already understood

1010

Problem: Too BroadProblem: Too Broad

Very broad area of interestVery broad area of interest ““I want to understand how people use the I want to understand how people use the

Internet”Internet” ““What factors influence the use of an What factors influence the use of an

interface?”interface?”

Solutions?Solutions?

1111

Problem: Too NarrowProblem: Too Narrow

Too narrowToo narrow““Do Females Use Technology X more than Do Females Use Technology X more than Males?”Males?”

Solutions?Solutions?

1212

Problem: Cannot be MeasuredProblem: Cannot be Measured

Cannot be measuredCannot be measured““Will this new information technology make society Will this new information technology make society better?”better?”

Solutions?Solutions?

1313

Problem: Trivial or Previously Problem: Trivial or Previously Answered Research QuestionsAnswered Research Questions

This is why we actually use literature– This is why we actually use literature– even in applied, business, or exploratory even in applied, business, or exploratory research.research.

Bringing an ‘old’ problem to a ‘new’ Bringing an ‘old’ problem to a ‘new’ discipline is not necessarily trivial.discipline is not necessarily trivial.

1414

So, what is a So, what is a goodgood research research problem statement?problem statement?

““The research problem is to investigate the The research problem is to investigate the presumed effect of A, B and C on X and Y presumed effect of A, B and C on X and Y in (population).in (population).

1515

Moving from General to SpecificMoving from General to Specific

““Could use of technology X affect society in a Could use of technology X affect society in a positive way?”positive way?”

““If we looked at two populations, one using If we looked at two populations, one using technology X and one not using it, would they technology X and one not using it, would they differ?”differ?”

““How is the use of technology X related to How is the use of technology X related to productivity and work satisfaction in task groups productivity and work satisfaction in task groups within population Y?”within population Y?”

1616

Example from Week 1Example from Week 1

Socioeconomic Status

Academic Ability

Academic Achievement

Math skillsLanguage

skills

IncomeJob

Prestige

GradesLevel of

Schooling attained

1717

Implications of Research Questions Implications of Research Questions for Statistical Analysisfor Statistical Analysis

1818

Type of Research QuestionType of Research Question Statistics Statistics

DescriptiveDescriptive Mean, frequencyMean, frequency

Complex DescriptiveComplex Descriptive Cross-tabulations, factor Cross-tabulations, factor analysisanalysis

Single factor difference questionsSingle factor difference questions T-test, one-way ANOVAT-test, one-way ANOVA

Complex or multifactor difference Complex or multifactor difference questionsquestions

Factorial ANOVAFactorial ANOVA

Basic associational questionsBasic associational questions CorrelationCorrelation

Complex or multivariate Complex or multivariate associational questionsassociational questions

Multiple RegressionMultiple Regression

1919

JustificationJustification

2020

Justifying Research ProblemsJustifying Research Problems

Explain what is not known about the problem.Explain what is not known about the problem.

Why does the problem matter?Why does the problem matter?

Provide documentation that this is actually a Provide documentation that this is actually a problem.problem. Available statistics?Available statistics? Available literature that shows that this is a needed Available literature that shows that this is a needed

area of inquiry?area of inquiry?

2121

What is What is notnot a Justification? a Justification?

No one has looked at it before.No one has looked at it before.

Literature has failed to address the issue.Literature has failed to address the issue.

You think its interesting.You think its interesting. If it is ‘interesting’ then there is probably a If it is ‘interesting’ then there is probably a

justification buried in there, but you have to justification buried in there, but you have to spell it out.spell it out.

2222

Justification as Justification as SignificanceSignificance of the of the Study (Creswell 2003)Study (Creswell 2003)

What are the ways that the study will add What are the ways that the study will add to the scholarly research/literature in the to the scholarly research/literature in the field?field?

How does the study improve practice?How does the study improve practice?

How might the study improve policy?How might the study improve policy?

2323

Turning Research Questions into Turning Research Questions into Testable HypothesesTestable Hypotheses

2424

Inductive Logic of Research in Inductive Logic of Research in Qualitative StudiesQualitative Studies

Generalizations are made, or Theories to Past ExperienceAnd Literature

Researcher Looks for Broad Patterns, Generalizations, or Theories from Themes or Categories

Researcher Analyzes Data to Form ThemesOr Categories

Researcher Asks Open-Ended Questions of ParticipantsOr Records Field Notes

Researcher Gathers Information

2525

The Deductive Approach in The Deductive Approach in Typical Quantitative ResearchTypical Quantitative Research

Researcher Tests or Verifies a Theory

Researcher Tests Hypotheses or Research QuestionsFrom the Theory

Researcher Defines and OperationalizesVariables Derived from the Theory

Researcher Measures or Observes Variables Using anInstrument to Obtain Scores

2626

Why not just rely on pure Why not just rely on pure observation?observation?

SubjectivitySubjectivity ““group A is nicer than group B”group A is nicer than group B”

RecallRecall What did you say to me last week about topic What did you say to me last week about topic

X?X?

Interpretations or conclusions that lack Interpretations or conclusions that lack convincing supportconvincing support ““most kids don’t care what their parents say”most kids don’t care what their parents say”

2727

HypothesesHypotheses

A good research question will produce one A good research question will produce one or more testable hypotheses.or more testable hypotheses.

Testable hypotheses predict a relationship Testable hypotheses predict a relationship between between variables variables (not concepts).(not concepts).

2828

Three Basic Kinds of HypothesesThree Basic Kinds of Hypotheses

Descriptive QuestionsDescriptive Questions Single variable descriptionsSingle variable descriptions

Central tendency, variability, percentagesCentral tendency, variability, percentages

AssociationalAssociational Non-directional relationship between variables.Non-directional relationship between variables.

DifferenceDifference Group ComparisonGroup Comparison

2929

Null hypothesisNull hypothesis

Null Hypothesis:Null Hypothesis: HH00: : μμ11 = = μμcc

μμ11 is the intervention population meanis the intervention population mean

μμcc is the control population mean is the control population mean

In English…In English… ““There is no significant difference between the There is no significant difference between the

intervention population mean and the control intervention population mean and the control population mean”population mean”

3030

Alternative HypothesesAlternative Hypotheses

Alternative Hypotheses:Alternative Hypotheses: HH11: : μμ11 < < μμcc

HH00: : μμ11 > > μμcc

HH00: : μμ11 ≠ ≠ μμcc

3131

Alternative HypothesesAlternative Hypotheses

Non-directional hypothesesNon-directional hypotheses Associations, not causalAssociations, not causal

DirectionalDirectional Increase in A increases BIncrease in A increases B Decrease in A decreases BDecrease in A decreases B

InverseInverse Increase in A decreases BIncrease in A decreases B Decrease in A increases BDecrease in A increases B

3232

Conventions in Stating HypothesesConventions in Stating Hypotheses

Null hypothesis often not stated Null hypothesis often not stated Completely depends on convention in a given Completely depends on convention in a given

disciplinediscipline

Three basic approaches to using variables in Three basic approaches to using variables in hypotheses:hypotheses: Compare groups on an independent variable to see Compare groups on an independent variable to see

impact on dependent variableimpact on dependent variable Relate one or more independent variables to a Relate one or more independent variables to a

dependent variable.dependent variable. Describe responses to the independent, mediating, or Describe responses to the independent, mediating, or

dependent variable.dependent variable.

3333

Things to consider when stating Things to consider when stating hypotheseshypotheses

Know what you want to explain: dependent Know what you want to explain: dependent variablevariable One common problem is under-specifying the key DV One common problem is under-specifying the key DV

or DV’sor DV’s

The independent variable(s) should have The independent variable(s) should have variationvariation

Consider more than one independent variable, Consider more than one independent variable, especially factors for which you might want to especially factors for which you might want to “control”“control”

3434

Exploratory versus ConfirmatoryExploratory versus Confirmatory

Exploratory ResearchExploratory Research Often just testing to see if there are Often just testing to see if there are

associations between one or more variables.associations between one or more variables.

Confirmatory ResearchConfirmatory Research The more your topic has been researched, The more your topic has been researched,

the more likely that you will be engaging in the more likely that you will be engaging in some type of confirmatory research.some type of confirmatory research.

3535

An Example ModelAn Example Model

Socioeconomic Status

Academic Ability

Academic Achievement

3636

Next Week:Next Week:

Causation, Validity and ReliabilityCausation, Validity and Reliability

Read over the online “Read over the online “Layman’s GuideLayman’s Guide” to ” to Research MethodsResearch Methods