Power analysis — correlation
Sample size or power to detect a Pearson correlation, using the exact distribution of r (or the Fisher z approximation).
Menu: Analyze → Power Analysis → Pearson Correlation…
When should I use it?
- Planning a correlational study.
What are the assumptions?
- Bivariate normal data.
How do I run it in StatLab?
- Give ρ under H1 (and H0, usually 0), tails, α and the target power.
How do I read the output?
| Output | Meaning |
|---|---|
| Critical r | Smallest |r| that would be significant. |
| Total sample size / Actual power | Result of the search. |
Worked example
On the practice survey dataset (File → Sample dataset), this command — which the dialog's Paste button also produces — runs the procedure:
PROC pwCorrelation /mode=n /rho=0.3 /rho0=0 /tails=2 /method=exact /alpha=0.05 /power=0.8.
Output tables: Power — correlation: bivariate normal model (a priori).
How would I report it in APA style?
A sample of 84 gives power .800 to detect the stated effect at α = .050.
Computed by StatLab's validated procedure code when this page was built. The example only illustrates the steps; choose variables that fit your own research question.
What are common mistakes?
- Forgetting that small correlations (r = .1) need hundreds of cases.