💥 Effect Size §

= the strength of the relationship between two variables in a population → the magnitude of effect Measures either:

• size of association between variables
• size of difference between two group means

🧪 Formulas: §

🔠 Categorical data §

Cramèr’s V: §

$X^2=$ chi-saquared statistics $k=min(rows,columns)$ $N=$ population size

$V=\sqrt{\frac{X^2}{N(k-1)}}$

🌊 Continuous data §

Cohen’s d §

→ use when variances and sample size are the same

Glass’$\Delta$ §

→ use when variances are different, but sample size are the same

Hedge’s g §

→ use when variances and sample size are different

Also §

• independent of sample size
• larger effect size → larger test power