Nov8. Complex Experimental Designs

Complex Experimental Designs

Overview

Key Topics Covered

  • Definition of factorial designs

  • Explanation of IV x PV (Independent Variable by Participant Variable) designs

  • Methods of participant assignment in factorial designs

  • Expansion possibilities for factorial designs

Simple Experiments Recap

  • Basic experiments involve one IV with two levels:

    • Example Study:

      • IV: Alcohol Intake (Placebo vs. Drunk)

      • DV: Aggression measured by intensity and duration of shocks

      • Results are shown with a graph illustrating the effects of different conditions.

Factorial Designs

  • Factorial Design: A Research design with two or more IVs (called factors in this experimental design).

  • Pro: Allows exploration of interaction effects between variables, which cannot be done with two single-factor designs

  • To examine more complex, real-life situations researchers often add more than 1 IV to their study design

Interaction Effects

  • Interaction Effects: An interaction occurs when the effect of one IV depends on the level of another IV.

  • Example: Temperature of food and type of food affect preference (e.g., cold pancakes vs. hot pancakes).

Common Factorial Designs

  • In most common factorial designs, researchers cross the IVs - they study all possible combinations of the IVs.

  • Example 1: Effect of alcohol and body weight on aggression.

    • IV1: Alcohol intake (Placebo/Drunk)

    • IV2: Body weight (Light/Heavy)

    • DV: Aggression level measured.

Factorial Design Examples

  • Example 2: Investigated if thinking about alcohol influences aggression:

    • IV1: Photo Type (Alcohol/Plant)

    • IV2: Word Type (Aggressive/Neutral)

    • DV: Reaction Time.

  • Main Effects: Assessing the independent effect of each IV on the DV.

  • Interaction Effect: Evaluation of combined impacts shown on graphs.

3 results to inspect

  1. Main effect of IV 1

  2. Main effect of IV 2

  3. Interaction effect

Is there a significant diff. btwn levl1 vs. lvl. 2? in word type?

Is there a significant diff. in photo type vs. lvl. 1 vs. lvl. 2?

Results: Interaction effect

While it is possible to compute interaction effects from a table, it is sometimes easy to notice them on a line graph

  • can also notice the interaction on a bar graph

Assigning Participants

  • Methods:

    • Independent Groups Design: Different participants for each condition.

    • Repeated Measures Design: Same participants across all conditions.

  • Both designs can be combined in more complex experiments.

Types of Factorial Designs

  • Factorial designs can vary in complexity based on the number of levels and IVs:

    • Examples:

      • 2x2 (two IVs with two levels each)

      • 2x3 (two IVs: one with two levels and another with three levels)

      • ... and so on for more factors and levels.

Key Terms to Review

  • Factorial design

  • Interaction

  • IV x PV design

  • Levels

  • Main effect

  • Mixed factorial design

Review Questions

  • Why use multiple levels for an IV?

  • Definition and reasons for using factorial designs.

  • Main effects vs. interactions in data analysis.

  • Usefulness and conditions for IV x PV designs.

Next Steps

  • Submit research proposal revisions by the end of the day on November 8th.

  • Data matching study designs will be provided next week.