Single case, quasi experimental and developmental research

Single case, quasi experimental and developmental research

1. Single case experimental designs

   • Also called single participant designs
     • Subject's behaviour is measured over time during a baseline control period
     • Change from baseline to treatment periods is evidence of the effectiveness of the manipulation
   • Reversal designs
     • A (baseline), B (treatment), A (baseline)
       • Can also be ABAB or ABABAB
     • Also called a withdrawal design
     • Tests what happens when the treatment is removed
   • Multiple baseline designs
     • Effectiveness of treatment shown if behaviour changes after the manipulation
     • Observed under multiple circumstances

2. Program evaluation

   • Research on programs that are proposed to achieve a positive effect on a group
   • Needs assessment
     • Is there actually a problem?
   • Program theory assessment
     • How will the problem be addressed?
   • Process evaluation
     • Is the program addressing the needs properly?
   • Outcome evaluation
     • Are the intended outcomes being realized?
   • Efficiency assessment
     • Is the cost of the program worth the outcome?

3. Quasi experimental design

   • Used when true experimental designs cannot be achieved
   • One group post test only design
     • Lacks a control group and random assigment
     • Ex - time it takes a stranger to get up after sitting beside them
   • One group pre test post test only design
     • Change from the pre and post test can be computed
   • Non equivalent control group design
     • Employs a control group but two conditions are not equal b/c random assignment is not used
   • Non equivalent control group pre test post test design
     • Assignment is not random
     • Can compare pre test/post test results
   • Interrupted time series design
     • Multiple pre tests and post tests to examine natural manipulations in society
   • Control series design
     • Same as interrupted time series design, but with a control group

4. Threats to internal validity

   • History
     • An event that occurs that is not part of the manipulation
   • Maturation
     • People changing over time
   • Testing
     • Simply taking the pre test can change behaviour
   • Instrument decay
     • The measuring instrument or the way participants use it changes over time
   • Regression towards the mean
     • Occurs when participants are chosen for high/low scores

5. Developmental research design

   • Longitudinal cross sectional method
     • Same group of people are studied at different points in time
   • Cross sectional method
     • Persons of different ages are studied at one point in time
   • Sequential method
     • Begins with the cross sectional methods, then studies the same groups with the longitudinal method