Experimental Designs and Quantitative Data
Experimental Designs
- Experimental designs are valuable for inferring causality.
- Involve manipulating an independent variable and observing its impact on a dependent variable.
- Two types: between subjects and within subjects.
Between Subjects Design
- Participants are assigned to two or more groups (e.g., treatment and control).
- Also known as between-groups design.
- Random allocation helps ensure groups are similar at the start, reducing the risk of other factors explaining differences.
- Participants don't get to choose their group, which can lead to dropouts.
- Single-blind study: participants don't know their group assignment.
- Double-blind study: neither participants nor researchers know group assignments.
- More groups require larger sample sizes.
- Power analysis: calculation to determine the number of participants needed in each group.
Within Subjects Design
- The same participants are measured more than once on the dependent variable.
- Common example: pre-post design, measuring a variable before and after an intervention.
- Reduces variability caused by individual differences.
- Longitudinal data: collecting data over time from the same participants.
- Single-case experimental design (SCED): focuses on whether an intervention works for a specific individual.
- SCEDs account for individual responses, unlike typical pre-post designs that aggregate data.
Drawbacks of Within Subjects and Longitudinal Designs
- Practice effects: participants may improve simply due to familiarity with the task.
- Maturation: performance may change naturally over time.
- History effects: external events (e.g., a pandemic) can influence results.
- Attrition: participants dropping out over time can reduce reliability.
Types of Quantitative Data
- Four categories: observational behavioral data, self-report data, informant reports, and life outcome data.
Observation of Behavior (B Data)
- Data collected from direct observation of behavior.
- Examples: reaction time.
- Often considered more objective.
Self Report
- Individuals provide information about themselves (thoughts, feelings, behaviors, attitudes).
- Collected through questionnaires, surveys, interviews, or focus groups.
- Strength: direct access to inner experience.
- Limitations: recall bias and social desirability bias.
- Information provided by someone who knows the person well.
- Useful for cross-checking self-reports or when working with children.
Life Event Data
- Objective outcomes that link psychological variables to real-world events.
- Examples: GPA, employment history, medical records.
- Provide context for interpreting psychological findings.