Topics in SPED Research Session 6: Qualitative Research Methods
Dec 13, 2015
Topics in SPED Research
Session 6: Qualitative Research Methods
Review for Quiz, Take Quiz Discussion Brief Lecture In-Class Activity Research Proposal work
Agenda
Prepared by M. Hara ([email protected])
Statistics, statistics
Descriptive StatisticsWho is in your data?
sample population
Inferential StatisticsWhat your sample says about the population
sample
population
Mean, Median, Mode, Standard Deviation, Variance Tests of significance
(t-, F-Tests)
Tests of Significance Statistical analyses to determine whether a
difference is statistically significant (probability for result to occur by chance).
Yes or No answer
Alpha level (p=)◦ An established probability level which serves as the
criterion to determine whether to accept or reject the null hypothesis
◦ Common levels in education .01 .05 .10
Objectives 4.1 & 6.1
http://www.youtube.com/watch?v=0zZYBALbZgg
Chi-square explained (short video) http://www.youtube.com/watch?v=
WXPBoFDqNVk
Linear Regression (short video) http://www.youtube.com/watch?v=
ocGEhiLwDVc
Videos on Testing Hypotheses Using Statistics
Equality of variance Level of Spread in Distribution is equal Variance= average squared deviations between
a group of observations and their respective means.
http://www.youtube.com/watch?v=3BApSAESfxI Video Reference Above A common assumption of statistical analyses If not met, results are not valid Need to use a non-normally distributed statistic
like Levene’s Test
Homogeneity of Variance
T tests- used when have two groups to compare. ◦ Independent samples t- if groups are independent
Different people in each group◦ Dependent samples t-: if two sets of scores are available for the same
people Matched groups
ANOVA (analysis of variance)- when you have more than 2 groups to compare OR more than one independent variable (reports an F-statistic, which is basically a t-value squared)
ANCOVA (analysis of covariance)- ANOVA that allows for control of the influence of an IV (e.g., characteristics of people) that may vary between your groups before treatment is introduced. ◦ Post-hoc method for matching groups on variables such as age, prior
education, SES, or a measure of performance
Inferential Statistics
To determine if the differences between groups or interventions are significant. ◦ Probability of the difference of groups of interventions being by
chance. p=.01 (1% probability the difference is due to chance) p=.10 (10% probability the difference is due to chance)
◦ p less than .05 commonly used to determine significance◦ Use t-tests, F-tests (ANOVA & ANCOVA) to determine significance
To determine the effect of our interventions◦ After you have determined that the difference was significant,
statistically…want to know the amount of the change◦ Based on number of participants, etc.◦ Example, weight loss program claims average weight loss of 30
pounds (effect size)◦ Don’t know if every participant lost exactly 30 pounds or if half
lost 60 pounds and the other half lost no weight at all!
Why do we use statistics?
Review for Quiz
Steps in the Research/Scientific Process
1. Identify socially important issue
2. Review current literature
3. Define conceptual model
4. Define specific hypothesis(es) and research question(s)
5. Define dependent variable(s)/measure
6. Identify independent variable(s)/measures
7. Select appropriate research design
8. Obtain consents 9. Collect data 10. Analyze data 11. Communicate
results Written presentation Oral presentation
Prepared by M. Hara ([email protected])
Variable Types and Analysis
13
DependentVariable
IndependentVariable
Is therean association?
(a.k.a., Outcome) (a.k.a., Predictor, Intervention)
Where differences culminate
ContributingFactors
Prepared by M. Hara ([email protected])
Categorical
Numerical/Continuous
Categorical
Numerical/Continuous
Contingency Tables(a.k.a. Cross-tabs)
Variable Types and Analysis
14
DependentVariable
IndependentVariable
Chi-square testOr χ²-test
Prepared by M. Hara ([email protected])
Categorical
Numerical/Continuous
Categorical
Numerical/Continuous
Analysis of Variance
(a.k.a. ANOVA)
Variable Types and Analysis
15
DependentVariable
IndependentVariable
Prepared by M. Hara ([email protected])
Variable Types and Analysis
16
DependentVariable
IndependentVariable
CategoricalNumerical/Continuous
Analysis of Variance(a.k.a. ANOVA)
SAT9 Math Score
Males Females
t-test or F-test
Prepared by M. Hara ([email protected])
Categorical
Numerical/Continuous
Categorical
Numerical/Continuous
Regression
Variable Types and Analysis
17
DependentVariable
IndependentVariable
Prepared by M. Hara ([email protected])
Variable Types and Analysis
18
DependentVariable
IndependentVariable
Numerical/Continuous
Numerical/Continuous
Regression
SAT9 Math Score
Household Income
Prepared by M. Hara ([email protected])
Categorical
Numerical/Continuous
Categorical
Numerical/Continuous
Logistic Regression
Variable Types and Analysis
19
DependentVariable
IndependentVariable
Prepared by M. Hara ([email protected])
Variable Types and Analysis
20
DependentVariable
IndependentVariable
Numerical/ContinuousCategorical
Logistic Regression
High school Exit Exam
SAT 9 Math
Fail
Pass
Probability of passing h.s. exam based on SAT-9 score
Investigators attempt to determine the cause of differences that already exist between or among groups of individuals.
Describes conditions that already exist (a.k.a. ex post facto).
The group difference variable is either a variable that cannot be manipulated or one that might have been manipulated but for one reason or another, has not been.
Studies in medicine and sociology are causal-comparative in nature, as are studies of differences between men and women.
What is Causal Comparative Research?
Similarities and Differences Between Causal-Comparative and Experimental Research Similarities
Require at least one categorical variable Both compare group performances to determine relationships Both compare separate groups of subjects
Differences In experimental research, the independent variable is manipulated Causal studies are likely to provide much weaker evidence for
causation In experimental studies, researchers can assign subjects to
treatment groups The researcher has greater flexibility in formulating the structure of
the design in experimental research
Similarities Ex Post Facto research Attempt to explain
phenomena of interest Seek to identify variables
that are worthy of later exploration through experimental research
Neither permits the manipulation of variables
Attempt to explore causation
Differences Causal studies compare two
or more groups of subjects Causal studies involve at
least one categorical variable
Similarities and Differences Between Causal-Comparative and Correlational Research
Examples of the Basic Causal-Comparative Design
Step 1- Determine Purpose
Step 2- Identify a Sampling Plan & Mode
Step 3- Design survey instrument
Step 4- Test survey instrument
Step 5- Send out a letter of transmittal
Step 6- Deliver the survey
Step 7- Analyze data from survey
Steps to designing, delivering, and analyzing surveys
Quiz Questions
27
Correct Quiz
Discussion
Break
Qualitative Methods
"All research ultimately has a qualitative grounding"- Donald Campbell
“Truth is relative..”◦ Albert Einstein
Lecture
Prepared by M. Hara ([email protected])
My Data, My Evidence
What/how much do I need to know?
Depth of Information
Qualitative DataQualitative Data
Quantitative DataQuantitative Data
Prepared by M. Hara ([email protected])
My Data, My Evidence
Addressing “WHY” questions?
Depth of Information
Qualitative DataQualitative Data
Quantitative Data
Prepared by M. Hara ([email protected])
My Data, My Evidence
Addressing “WHY” questions?
Depth of Information
Qualitative DataQualitative Data
Quantitative Data
• Focus Groups
• Interviews
• Case Studies
• Observation
Prepared by M. Hara ([email protected])
My Data, My Evidence
Addressing “WHY” questions?
Depth of Information
Qualitative DataQualitative Data
Quantitative Data
• Focus Groups
• Interviews
• Case Studies
• Observation
Details, Depth, and Variability
Representative, Generalizability
Prepared by M. Hara ([email protected])
My Data, My Evidence
Addressing “WHAT” questions?
Depth of Information
Qualitative Data
Quantitative DataQuantitative Data
Prepared by M. Hara ([email protected])
My Data, My Evidence
Addressing “WHAT” questions?
Depth of Information
Qualitative Data
Quantitative DataQuantitative Data• Survey • Large Scale Assessments
Prepared by M. Hara ([email protected])
My Data, My Evidence
Addressing “WHAT” questions?
Depth of Information
Qualitative Data
Quantitative DataQuantitative Data
Representative, Generalizability
Details, Depth, and Variability
• Survey • Large Scale Assessments
Prepared by M. Hara ([email protected]) 38
ORQuantitative Data
Representative, Generalizability
Qualitative Data
Details, Depth, Variability
EvidenceBest
Prepared by M. Hara ([email protected]) 39
Quantitative Data
Representative, Generalizability
Qualitative Data
Details, Depth, Variability
EvidenceBest
AND
Qualitative Research
why and how of human behavior◦ Work with a range of models, theories, pertaining to
human phenomena◦ Involve small groups of participants; interpretation &
reflection◦ Speech and texts, and their interpretation are very
important◦ People's accounts of their actions significant◦ Not Positivist: no objective truth; different
interpretations; no final certainty in knowledge
Qualitative issues
Qual: Requires a different way of thinking to address issues like:◦ Reliability: repeatable with same/comparable
results◦ Validity: relationship between conditions and
results◦ Generalizability: historical and cultural limitations
When is Qualitative Research Useful? Qualitative research relies on imprecise
and everyday notions of what is valid, etc. But it does so reflexively; in a self-aware
and theoretically-mediated manner. Qualitative is useful in relationship to
quantitative if:◦ The topic has been researched for a long time
in the same way◦ The topic is new to research◦ You would like in-depth information that may be
difficult to convey quantitatively
Compare and contrast qualitative research & quantitative research
Qualitative v.'s Quantitative
QualitativeResearch
QuantitativeResearch
Type of questions Probing Limited probing
Sample Size small large
Info. Perrespondent
much varies
Admin Requires skilledresearcher
Fewer specialistskills required
Type of Analysis Subjective,interpretative
Statistical
Type of research Exploratory Descriptive orcausal
Popularity of Qualitative Research1 Usually much cheaper than quantitative
research2 No better way than qualitative research to
understand in-depth the motivations and feelings of participants
3 Qualitative research can improve the efficiency and effectiveness of quantitative research
Characteristics of Qualitative Research Takes place in the natural setting Uses multiple methods that are interpretive Is emergent rather than tightly prefigured Fundamentally interpretive (role of researcher as
interpreter) Researcher views social phenomena holistically Researcher systematically reflects on who he or
she is in the inquiry and is sensitive to hiw or her personal biography and how it shapes the study
Researcher uses complex reasoning that is multifaceted, iterative, and simultaneous
Researcher adopts and uses one or more strategies of inquiry
Main types of qualitative research
1. Ethnographic2. Case Study3. Phenomenological 4. Grounded theory5. Participatory research6. Clinical research7. Focus groups
Concerned with the collection & analysis of empirical data drawn from “real world” contexts rather than being produced under experimental conditions created by the researcher.
Research involves sustained engagement in a particular site.
Key aim is for the researcher to attempt to make sense of events from the perspectives of participants.
Data are gathered from a range of sources, but observation and/or relatively informal conversations are often key tools.
Focus is a single setting or group of relatively small scale or a small number of these…or one individual
Analysis of the data involves interpretation of the meanings & functions of human actions & mainly takes the form of verbal descriptions & explanations, with quantification & statistical analysis playing a subordinate role at most.
Ethnographic research
An approach that involves an in-depth exploration of a single case, or example, of the phenomenon under study.
Could be an individual, group of individuals, a classroom, a school, or event.
Data collection includes:◦ Nature of the case◦ Its historical background◦ The physical setting◦ Other contexts, such as economic, political, legal, and aesthetic ◦ Other cases through which this case is recognized◦ Those informants through whom the case can be known
Case Study
Emphasizes the individual’s subjective experience. Research questions framed as: “What is the meaning,
structure, and essence of the lived experience of this phenomenon for this person or group of people?”
Ethnomethodology- ◦ Focus on how individuals recognize, describe, explain and
account for their everyday lives Conversational analysis
◦ Analyzes the sequential organization of topics, management of turn taking, and practices related to opening, sustaining, and closing a conversation.
E.g., Experience of being a student with a disability in a general education classroom.
Phenomenological research
A general methodology for developing theory that is grounded in data systematically gathered and analyzed.
Theoretical propositions are not stated at the outset of the study.
“Theory” emerge out of the data themselves and not prior to data collection.
Grounded theory
Cooperative participatory research◦ Involves participation of all people in the research process but
does not explicitly address power relations and the potential transformative effects of the research .
◦ Identify research problem & procedures collaboratively; implement procedures; review & interpret data to improve practice or guide additional research
Transformative participatory action research◦ Involves members of the community in the process in varying
roles, but does so with explicit recognition of power issues and a goal of transforming society.
◦ Researcher’s role= change agent ◦ Emphasizes the use of methods that allow the voices of the
oppressed to be heard.
Participatory research
Use of in-depth interviews & participant observation, the researcher can come to understand the multiple forces that influence the effectiveness of different types of therapy.
Clinical research
Data collection method or strategy for research.
Group interviews that rely, not on a question-and-answer format of interview, but on the interaction within the group.
Focus groups
Personal interviews, observations- guidelines for completing in text
Researcher as the instrument- ◦ Need to be clear who researcher is, assumptions,
and monitor throughout project Speaking for others
◦ Extreme caution should be used in speaking for others, especially those experiencing oppression
Research questions viewed as flexible…evolving
Data collection/methodology
Please get together with your research group
Complete the in-class activity sheet.
In-Class Activity