What is a Quasi-Experimental Design?

• ‘Quasi-’ means ‘almost’ – not fully experimental. • No random assignment to groups. • Used when randomization is unethical or impractical.

True vs. Quasi-Experiments

• True Experiment: Random assignment, manipulated IV. • Quasi-Experiment: No random assignment, often use natural groups. • Reduces internal validity due to possible pre-existing group differences.

Conditions of Causality

• Internal Validity: Reduced in quasi-experiments due to lack of random assignment. • External Validity: Can be higher than lab experiments if setting mirrors real life. • Important to match groups on key variables (e.g., SES, age).

• Nonequivalent Control Group (Posttest Only). • Nonequivalent Control Group (Pretest/Posttest). • Simple Interrupted Time-Series Design. • Time-Series with Nonequivalent Control Group.

Nonequivalent Control Group Design

• Comparison group is similar but not randomly assigned. • Pretest helps evaluate initial group equivalence. • Group differences at posttest may still reflect initial differences.

Interrupted Time-Series Design

• Observe DV across time points before and after a treatment. • Clear discontinuity suggests treatment effect. • Example: GPA over semesters, with an intervention after semester 4.

Time-Series + Nonequivalent Group

• Adds a comparison group to basic time-series design. • Improves validity by showing change in treatment group only. • Rules out some time-based threats (e.g., maturation).

Ex-Post Facto Designs

• Used to test hypotheses when manipulation isn’t possible. • E.g., Fraternity membership and appearance concern. • Use various quasi-designs to illustrate effects and rule out threats.

• Used in clinical or applied settings with few participants. • Allow detailed tracking of individual behavior over time.

Types of Small-N Designs

• Stable-Baseline Design: Long baseline followed by treatment. • Reversal Design: Treatment introduced, then removed. • Helps infer causality through behavior change patterns.

Help

Options

focusNode

Didn't know it?
click below

Knew it?
click below

Don't Know

Remaining cards (0)

Know

retry

shuffle

restart

0:00

Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.

Normal Size Small Size show me how

Experimental Psych

Quasi-Experimental Designs and Small N Studies


What is a Quasi-Experimental Design?	• ‘Quasi-’ means ‘almost’ – not fully experimental. • No random assignment to groups. • Used when randomization is unethical or impractical.
True vs. Quasi-Experiments	• True Experiment: Random assignment, manipulated IV. • Quasi-Experiment: No random assignment, often use natural groups. • Reduces internal validity due to possible pre-existing group differences.
Conditions of Causality	• Internal Validity: Reduced in quasi-experiments due to lack of random assignment. • External Validity: Can be higher than lab experiments if setting mirrors real life. • Important to match groups on key variables (e.g., SES, age).
Design Types	• Nonequivalent Control Group (Posttest Only). • Nonequivalent Control Group (Pretest/Posttest). • Simple Interrupted Time-Series Design. • Time-Series with Nonequivalent Control Group.
Nonequivalent Control Group Design	• Comparison group is similar but not randomly assigned. • Pretest helps evaluate initial group equivalence. • Group differences at posttest may still reflect initial differences.
Interrupted Time-Series Design	• Observe DV across time points before and after a treatment. • Clear discontinuity suggests treatment effect. • Example: GPA over semesters, with an intervention after semester 4.
Time-Series + Nonequivalent Group	• Adds a comparison group to basic time-series design. • Improves validity by showing change in treatment group only. • Rules out some time-based threats (e.g., maturation).
Ex-Post Facto Designs	• Used to test hypotheses when manipulation isn’t possible. • E.g., Fraternity membership and appearance concern. • Use various quasi-designs to illustrate effects and rule out threats.
Small-N Designs	• Used in clinical or applied settings with few participants. • Allow detailed tracking of individual behavior over time.
Types of Small-N Designs	• Stable-Baseline Design: Long baseline followed by treatment. • Reversal Design: Treatment introduced, then removed. • Helps infer causality through behavior change patterns.

Created by: scass423

"Know" box contains:
Time elapsed:
Retries: