Graphing & Research Designs Flashcards
Three variables of research designs
Independent variable: manipulated to produce a change in target beh (treatment)
Dependent variable: target behaviour measure
Confounding variable: another factor that may affect behaviour that is not controlled
What is a functional relationship?
Treatment procedure regularly causes a change in the target behaviour (behaviour changes as a function of the procedure)
Five categories of research designs
- A-B design
- A-B-A-B/reversal design
- Multiple baseline design
- alternating treatments design
- changing-criterion design
What is A-B design? Pros/cons
One baseline phase (A) and one treatment phase (B)
Pro = good for self-management
Con = lacks replication, not a true research design, no cause and effect
What happens in the baseline phase
Collect at least three data points that do not show a behavioural change trend
What is the A-B-A-B design? Pros/cons
Two baseline and two treatment phases
Observe same beh in same client
Can include more than one treatment type (A-B-A-C)
Pro = establish cause and effect
Cons = unethical to withdraw beneficial intervention, beh may not revert back in second baseline
What is multiple baseline design? What are the three kinds?
More than one A-B design carried out at once
1. Multiple baseline across subjects: apply treatment to several diff ppl
2. Multiple baseline across behaviours: apply treatment to several diff target beh
3. Multiple baseline across settings: apply treatment in several diff settings
Pros and cons of multiple baseline design
Pro = no reversals, good for behaviours that do not revert
Con = treatment may spread across subjects, behaviours or settings during baseline phase
What is alternating treatments design? Pros/cons
Baseline and treatments applied in rapid succession (treatment one day, baseline next, treatment next…)
Treatment effects shown by fractionation
Pros = extraneous variables have less effect, evaluate effects of diff treatments
Con = treatments interact?
What is fractionation
Consistent vertical separation between treatment curves
What is the changing-criterion design? Pros/cons
Criteria for successful treatment changes over time (more stringent)
Uses A-B design, goal for target beh changes in treatment phase
Pro = good for behaviours that can be approximated gradually
Con = unsuited for beh that cannot change gradually
Important parts of graph
x-axis/y-axis lines and labels (with units)
Numbers on axes
Data points and line connecting
Phase line(s) (separate A and B)
Phase labels (baseline, treatment, etc)
A functional relationship is established if…
- a target beh (DV) changes when an IV is manipulated, all other variables held constant
- process is replicated and beh changes each time
why isn’t A-B design a true research design
Is not replicated; does not rule out the possibility that an extraneous variable was responsible for the beh change; no functional relationship
Why would we stagger treatments in multiple baseline
If the behaviour changes only after treatment is given, we can say that the treatment, not an extraneous variable, caused the beh change
