The flashcards below were created by user
on FreezingBlue Flashcards.
Single-case experimental designs
- AB Design
- Baseline Behavior (A)
- -What are they typically like when nothing is going on
- Treatment (B)
- -Ex: give star for correct answers
- -Does the behavior change?
- Ex: Used on Autistic children
- -Baseline: How many times will question be asked before having interaction?
- -Treatment: Give candy for looking at the interviewer
- Measure Baseline
- Take away treatment
- See if behavior changes when treatment is taken away
- 1. Ethics
- •Don't want to end experiment on negative note
- 2. 2 Reversals
Multiple Baseline Design
- The effectiveness of the treatment is demonstrated when a behavior changes only after the manipulation is introduced
- 1. Across subjects
- 2. Across behaviors
- 3. Across situations (settings)
The behavior of several subjects is measured over time
Several different behaviors of a single subject are measured over time.
Across Situations (Settings)
- The same behavior is measured in different settings
- Ex: Home, work, or school
- Research on programs that are implemented to achieve some positive effect on a group of individuals
- 1. Needs Assessment
- 2. Program Theory Assessment
- 3. Process Evaluation
- 4. Outcome Evaluation
- 5. Efficiency Assessment
Studies whether there are problems that need to be addressed in a target population
Program Theory Assessment
The collaboration of researchers, service providers and prospective clients of the program to determine that the proposed program does in fact address the needs of the target population in appropriate ways.
- Program monitoring
- Evaluation researcher monitors it to determine whether it is reaching the target population
- Impact assessment
- Are the intended outcomes of the program being realized?
- Researchers must determine whether it is worth the resources it consumes.
- Cost of program must be weighed against its benefits
- Not a true experiment
- Half experiment
- Controlling environment and experiment but not the independent variable
- For true experiment: randomly assign people to different groups to be equivalent
- Ex: Gender, Alcoholism
- Impose treatment or Non-imposed treatment to manipulate environment
One-Shot Case Study
- One-Group Posttest-Only Design
- Participants --> IV --> DV
- Most basic type of Quasi Design
Ex: Participants --> Sit next to stranger (IV) --> Measure time until stranger leaves (DV)
One-Group Pretest-Posettest Design
Partcipiants --> DV Pretest --> IV --> DV Posttest
Ex: Participants --> Smoking Measure (DV Pretest) --> Training Program (IV) --> Smoking Measure (DV Posttest)
Nonequivalent Control Group Design
- Ex: Participants --> Training Program (IV) --> Smoking Measure (DV)
- Participants --> No Training Program (IV) --> Smoking Measure (DV)
Any confounding event that occurs at the same time as the experimental manipulation.
Any changes that occur systematically over time.
Taking a pretest changes behavior without any effect on the independent variable.
Basic characteristics of the measuring instrument change over time.
Regressions toward the mean
- Statistical regression
- Whenever participants are selected because they score extremely high or low on some variable.
- When score is so high or so low that the only way is toward to average
- "Sports Illustrated effect"
- -Athletes make the cover of magazine (highest point) and will start going down
Interrupted time series design
- Examine fatality rates over an extended period of time
- Before and after the reform was instituted.
- -Ex: Less people injured after Helmet Law
- •Last 5 years before Helmet Law and look at number of injuries and fatalities
- •Helmet Law is the interruption
- •5 years after Helmet Law and look at number of injuries and fatalities
- -Hard to give a control group
- •Choose state that doesn't have Helmet Law