Additional research designs Prof’s Speech – Purple Text
• Less control of extraneous variables
• Usually random assignment is missing; the groups are naturally occurring
• Doesn’t meet all the requirements for an experiment but has the nature of an experiment
• Sometimes called a field experiment
Some common features of quasi-experiments:
• matching instead of randomization
• time series analysis
• unit of analysis: not people – may be a group, organization, program, etc.
One Group Pre-post
Threats to Internal Validity
o The event affects the study outcome
Pre- and post- circumstances differ
o Change in subjects over time – differences can be based simply on age
Testing / Repeated testing
o can cause subjects to be more aware of their behaviour/make them want to change their
behaviour in subsequent tests
o people dropping out of the study
o certain types of people dropping out, will not make a difference to the study
o but other types can hinder the study
Regression to the mean
o High or low maintenance measurements followed by measurements closer to the group mean
Non -equivalent control group design
- With control group
- Selection bias – pre-existing differences between groups
Time Series Analyses
- Can’t randomize participants, but can get assignments of the dependent variable, pre- and post-treatment
Single-Case Research Designs
• Use only one case or group to investigate a specific phenomenon.
• Not the same as a case study.
• Uses time-series design.
• Take multiple pre and post-treatment measures.
Advantage of Small-N Design
• Participants from hard to find populations
• Results easy to interpret (often no stats)
• Can focus on helping one (few) participant(s)
- Problems: might not be able to end with the baseline condition because the effect may not be reversible
- Has a control group Multiple Baseline Design
• Testing a treatment effect when the effect is irreversible.
• Baseline data collected on:
• 2 or more behaviours for same individual
• Same behaviour for 2 or more individuals
• Same behaviour across 2 or more situations for the same individual.
Choosing a Research Method
- All research methods have advantages and disadvantages
- There is no one perfect method for everything
- Different methods are better suited for different experiments
The choice is affected by:
• Resources like time and money
• Ethical concerns – certain topics of study, i.e. child abuse, will have to greatly consider ethics)
• The research question should guide the choice of method
Description: asking what or how many, getting ideas about why, developing theory/How does the research
question guide the choice?
• Case study for unusual cases
• Ex. Nonverbal children, natural disaster, hostage-taking situations
• These circumstances cannot be created (because of ethical concerns)
• Case study for in-depth examination
• Ex. Merger of 2 companies
• Correlational study
Prediction: if I know X, can I predict Y?
• Correlational study
Causal: Verifying the why or how
- Ex. Does drug X lead to the relief of symptom Y?
• Experiment, quasi-experiment, field experiment
External validity ------------------------------------------- Internal validity
Simple Description Correlational St. Quasi Experiments “True” Experiments
Explore Relate measured Test hypotheses in Test specific
the Describe a variables to each naturally occurring hypotheses in
process of behaviour/social other to test the events or field controlled “lab”
trend hypothesis studies conditions
Analyzing your results
The type of data determines how you can analyse it. The type of analysis determines whether or not y