The big three
- How many variables are involved ?
- What is the data type of the involved variables ?
- Asymmetric vs symmetric ?
How many variables involved ?
- One : Univariate analysis (descriptive stats)
- Two : Bivariate analysis (inferential stats)
- More than two : multivariate analysis
What is the data type of the involved variables ?
- Nominal
- Ordinal
- Interval/Ratio
Asymmetric vs Symmetric ? (only important for bivariate techniques)
- Asymmetric when :
- Variables have different data type
- Predicting DV from IV ("causal" relationship)
- Else : Symmetric
Regression vs Correlation (with regards to interval data)
- When we want to establish a linear relationship/association (symmetric)
- Correlation
- When we want to predict one variable based on another variable : causal relationship (asymmetric)
- Regression analysis
Importance of k=2 or k>2
Don't do t-test if k>2 because of level of significance
Related vs unrelated sample
- Related sample
- Within-subjects design
- Each participant in each condition
- e.g. fairtrade & organic & control conditions
- Small sample needed and control for intra-individual effects
- Unrelated sample
- Between subjects design
- Each participant only in one condition
- e.g. fairtrade or organic or control conditions
- No practice effects or hypothesis guessing