Non-Experimental Design Flashcards
(23 cards)
Describe non-experimental design.
- No manipulation of variables, examine effects of existing differences (can be quantitative or qualitative)
- Qualitative research is often used to jump-start asking new questions or to develop quantitative measures
- May include verbal statements, direct quotes, excerpts, open-ended responses, etc.
- Inductive reasoning: data is collected to identify trends/themes to develop theories
- Often includes natural environments/situations
What are the goals of non-experimental designs?
- Observe, describe, document behavior or characteristics
- Examine relations among behavior or characteristics
- Compare characteristics
What are types of non-experimental designs?
- Descriptive
- Relationship
- Comparative
- Causal-comparative or Cohort
What are types of descriptive non-experimental designs?
- Surveys
- Case studies
- Prevalence studies
Describe surveys.
- Types of questions: yes/no, categorical, rating scale, cumulative response, open-ended
- Advantages: easy to test/score, can test large # people, may be standardized
- Disadvantages: difficult to craft questions (i.e. leading questions, social desirability, ambiguity), voluntarily/non-response bias, may be reliability but not necessarily valid
Describe case studies.
- Intense observation of an individual to understand their behavior
- Can utilize an experimental design
- Trade-off between gathering evidence in natural setting vs. having as much experimental control as possible
What are types of relationship non-experimental designs?
- Correlational
- Predictive (regression)
Describe correlational studies.
- Two variables that vary along a dimension (not groups)
- Examine if the extent of one relates to the extent of the other
Describe predictive/regression studies.
- Two or more variables
- Examine measures close in time/use to predict the future occurrence of another
What are types of comparative non-experimental design?
- Case-control
- Group comparisons
Describe case-control studies.
- Examines the degree to which people are one vs. the other
- Problems of restricted range, skewed sample (extreme participants)
Describe group comparison studies.
- Examines the impact of existing differences between 2+ groups on a measure of skill/characteristic
- EX: demographics, disorder vs. control
- Assumes everyone is either one or the other category
- Problem is unequal sample sizes
Describe causal-comparative studies.
-Obtain several measures per participant in order to control for possible alternative explanations
Compare longitudinal vs. cross-sectional studies.
LONGITUDINAL
- Better control for other differences between groups
- Slower to run
- More participant drop-out (attrition)
- Order effects
CROSS-SECTIONAL
- Groups may differ on factors besides age
- Faster to run
- Attrition not a factor
- Particiapnts are naive
Describe naturalistic observation studies.
- Ethology: the study of naturally-occurring behavior
- Method: making detailed observations of animals/humans in their natural settings
Describe ethnography studies.
- Systematized form of participant observation
- Describe patterns of behavior that characterize a culture in natural settings
- Fieldwork, behavior, artifacts, speech samples
Describe grounded theory.
- No presumptions; data direct the development of the theory and refine repeatedly
- Analysis: open coding, axial coding, selective coding
What is open coding?
-Read through many times to summarize patterns
What is selective coding?
-Finding core variable across all data
What is axial coding?
-Defining relationships
Describe phenomenology studies.
- Verbal transcript of narrative
- Holistic sense
- Identify parts (meaning changes)
- Re-wording to capture underlying meaning
- Generate a written description of the structure of an event
Describe conversion analysis.
- Recordings of conversational interactions
- Measures: orthographic transcripts
- Analysis of transcripts: intended actions, turn-taking , how other person responds, prosodic features
What is examined with scientific rigor?
- Researcher bias: reflectivity, negative case sampling, research triangulation
- Descriptive adequacy: demonstrate factual accounting (i.e. methods/data triangulation, thick description)
- Interpretative adequacy: how well study captured/conveyed the meaning of an experience
