Methods 3 Flashcards
4 ways X & Y can be correlated
- X may be causing Y
- Y may be causing X
- Some underlying variable Z may be causing both X and Y
- X may be causing Q which causes Y (Q is the mediator)
Definition of Experiment
A study in which an intervention is deliberately introduced to observe its effect
What are independent variables in consumer behavior
The marketing mix elements
What are the dependent variables in consumer behavior
Market outcome/behavior
4 types of independent variables
- Manipulated variables
- Treatment variables
- Intervention
- Factor
2 types of dependent variables
- Effect
- Outcome
3 necessary factors for Causality
- Correlation
- Temporal Antecedence
- No third alternative factor driving both
Definition of Random Assignment
Creates two or more groups of units that are probabilistically similar to each other on the average
Definition of Within-Subject Design
People are not divided by the conditions but see both conditions concurrently
-> Does not require a random assignment
Definition of Between-Subject Design
People in each condition group only see their condition
Pros & cons of Within-Subject Design
Pros
1. Can isolate individual differences
2. Requires fewer participants
Cons
1. Learning/carry-over effect
2. Fatigue effect
Pros & cons of Between-Subject Design
Pros
1. Each individual measurement is independent
2. Not influenced by learning or fatigue effects
Cons
1. Need larger number of participants
2. Individual differences/environment variables
Definition of Internal Validity
The ability of an experiment to show a causal relationship between IV & DV
Definition of External Validity
The applicability of experimental results to situations external to the actual experimental context
4 types of threats to Internal Validity
- Selection
-> Non-equivalent groups - History
-> Effect of time on environments - Maturation
-> Effect of time on subjects - Testing/Practice effect
