Single-Subject Experiments

Advantages

• Group means could conceal patterns that appear in individuals' data
• Big effects - only clinically significant effects are likely to be found
• Ethical and practical advantages (eg; can not withhold treatment; too few subjects)
• Flexibility

Disadvantages

• Can not examine any between-subject effects
• Can not detect small effects
• May be less generalizable

Control Strategies in Single-subject Research

• A-B Design (Stable Baseline)
• A-B-A Design
• Baseline, treatment, withdrawl
• Problems:
• Treatment may not be reversible
• May not be ethical to leave the subject in the untreated condition
• A-B-A-B Design (Repeated Treatments Design)
• A-B-A-B-BC-B-BC (Interaction Design)
• For examining the effects of 2 variables
• Obeys the cardinal rule of single-subject designs: Change only one thing at a time!
• Multiple Baselines Design
• Introduce the treatment at different times for different behaviors
• Really has multiple DVs and related IV's; example:
• IV1 = reward behavior A
• DV1 = frequency of behavior A
• IV2 = reward behavior B
• DV2 = frequency of behavior B
• Changing Criterion - changing the criterion for measuring a change in behavior as learning takes place (because some learning is irreversible)

Contrasting the means of Experimental Control in single-subject vs. group designs

• Group Designs - Control = eliminating confounds
• Single-Subject designs - Control = reducing error variance

(Although this contrast between single-subject and group designs is not a hard and fast rule, it is still a useful generalization.)