Strategic Planning Approaches

Study Notes

Single-factor designs have one independent variable (IV)
Four types of single-factor designs: independent groups, matched groups, nonequivalent groups, and repeated measures
Independent groups designs use separate groups for different levels of the IV
Matched groups designs attempt to create equivalent groups by matching participants on relevant variables
Nonequivalent groups designs use existing groups that are not equivalent
Repeated measures designs expose the same participants to all levels of the IV

To study nonlinear effects—the relation between the IV and DV might not be linear
To rule out alternative explanations

Goals of Ebbinghaus memory research: to understand how memory declines over time.
Methodology: focused on how long it took to re-learn the material, which was used to estimate the amount that had been lost over time
Results: showed rapid initial forgetting followed by a more gradual decline, demonstrating the forgetting curve

Placebo control groups: participants receive a fake treatment to control for the placebo effect
Waiting list control groups: participants are placed on a wait list to control for motivation
Yoked control groups: experimental participants in a study are “yoked” to subjects in a control group

Between-subjects designs (independent groups): separate groups for each level of IV, one group per level
Research examples presented in the slides involve note-taking types, social skills training, and traumatic brain injury
Some factors presented as possible subject variables—measured not manipulated

Between-subjects (multilevel) designs: used to investigate nonlinear effects, such as the inverted U-shaped relationship between arousal and performance
Research examples presented in the slides involve note-taking types, social skills training, and traumatic brain injury, number of children, and listening experiences.
Historical example of stroop effect (discussed)

Bar graphs are used to display data from independent groups designs
Line graphs are used to display data from repeated-measures designs
Ebbinghaus forgetting curve (described and displayed graphically)
Statistical tests: t-tests, one-way ANOVAs (one-way for independent groups designs, two-level factorial designs), and post-hoc testing

Factorial designs include more than one independent variable
IVs are also referred to as "factors"
Notation system is used to describe a factorial design, e.g., 2x3, 2x4x4, 3x2, etc.

The overall effect of an IV is a main effect—can be calculated by averaging scores across levels of all other variables
Interaction occurs when the effect of one IV depends on the level of another IV

Decision tree for factorial designs, guiding selection among different factorial designs
Different types of factorial designs: independent, matched, nonequivalent groups, repeated measures, mixed, P x E (interaction)

Sampling issues in survey research are more important than in other types of psychological research
Four methods for collecting survey data: In-person interviews, written surveys, phone surveys, and electronic surveys
Survey questions can be open-ended or closed-ended
Likert scales are often used to measure attitudes

Correlation: describes the relationship between two variables without suggesting causality
Scatterplots are graphical representations of the relationship between two variables
A correlation coefficient reflects the strength and direction of a linear relationship
Types of correlations: positive, negative, and zero
Regression: used to predict the value of one variable based on the value of one or more other variables

Directionality problem: it is not possible to say definitively that one variable causes another based on a correlation
Cross-lagged panel correlation can help address the directionality problem by measuring variables at different points in time
Mediator variables help explain how or why a relationship exists between two variables
Moderator variables specify the conditions under which a relationship exists