Research Methods (11)

• Factor: an IV in an experiment, especially those that include two or more IVs

• Factorial Design: a research design that includes two or more factors (IVs)

  • A two-factor design has two IVs

  • A single-factor design has one IV

What is a Factor and a Factorial Design?

• Each factor is crossed with each other factor

  • Number of Conditions = the product of the number of levels of each factor

  • EX) 2 (Time: Short vs. Long) x 2 (Usage Style: Passive vs. Active) Factorial Design

    • 2 * 2 = 4 Conditions

  • EX) 2 (Time: Short vs. Long) x 2 (Usage Style: Passive vs. Active) x 2 (Gender: Male vs. Female) Factorial Design

    • 2 2 2 = 8 Conditions

Why does the Number of Conditions matter?

• Interaction Effect:

  • The effect that factor A has on the DV depends on factor B

• EX) The effect of time spent on instagram on emotional well-being changes as a function of Instagram usage style

What is an Interaction?

• If a study shows main effects and interactions, the interaction is always more important

  • Real differences in marginal means, but an interaction is more exciting

• Most outcomes in psychological studies are not main effects, but interactions.

How are interactions more important than main effects?

• Cross-over Interaction “It depends”

  • In this example, if you are trying to find out if people like cold or hot food. The answer is it depends on what food you give them. Hot or cold pancakes? Hot or cold ice cream?

• Spreading Interaction (using “only when” or “especially when”)

  • In this example, the dog sits only when you have a treat.

What kind of Interactions are there?

11.2

Module done

• The potential to blend several different research strategies within one study

• That sort of potential develops studies that address scientific questions that could not be answered by any single strategy

What does mixing designs within a single research provide?

• Uses both within- and between-subjects design

  • It is a factorial study that combines different research designs

    • It is used when one factor is expected to threaten validity

• A common example of a mixed design is a factorial study with one between-subjects and one within-subjects

What are mixed designs?

• Basic concepts of a two-factor research design can be extended to more complex designs involving three or more factors

  • Such as designs are referred to as higher-order factorial designs

• In three-factor designs, main effects for each of the three factors are evaluated

• Defining and interpreting higher-order interactions follows the pattern set by two-way interactions

• Though more factors can be added without limit, more than three factors produce complex results that can be difficult to understand

What are Higher-Order Factorial Designs?

• Depends partly on whether factors are:

  • Between-Subjects

  • Within-Subjects

  • Some mix of both

• The standard practice includes:

  • Computing the mean for each treatment condition (cell)

  • Using ANOVA to evaluate the statistical significance of the mean differences

What is the Statistical Side of Factorial Designs?

11.3 - Applications of Factorial Design

Module Done

• Replication

  • Repeating the previous study by using the same factor or IV as it was used prior

• Expansion

  • Adding a second factor in the form of new conditions or new participant characteristics

What is Replication and Expansion?

• Using a participant variable as a second factor

  • Reducing the variance within groups by using a specific variable as a second factor.. Meaning to create a two-factor study

    • Greatly reduces individual differences within each group

    • Does not sacrifice external validity

How do you reduce variance in a between-subjects design?

• Using order of treatments as a second factor

  • This makes it possible to evaluate any order effects existing in the data

  • Three outcomes can occur:

    • No order effects

    • Symmetrical order effects

    • Nonsymmetrical order effects

How do you evaluate order effects in a within-subjects design?