Sample Size
Methodology & design
The number of observations in a study; adequate size is needed for statistical power and credible estimates.
Sample size is the number of units from which data is collected, and it drives statistical power, precision and the credibility of your results. Too small and real effects go undetected; needlessly large and you spend resources for negligible gain.
The defensible approach is a priori power analysis in G*Power: specify the smallest effect worth detecting, set alpha at 0.05 and power at 0.80, and solve for N. For finite populations, Cochran's or Yamane's formulas give a required size for a chosen margin of error and confidence level.
Rules of thumb circulate widely — ten cases per predictor in regression, 200 or more for covariance-based SEM, the ten-times rule for PLS-SEM — but they are weaker justification than a power analysis. In qualitative research the logic changes entirely: sample size is governed by data saturation rather than calculation. Always report the achieved sample alongside the target and explain any shortfall.
Where it's used
- Power-based planning before data collection
- Defending analysis choices at proposal and viva stage
Software used
Guides that use this concept
All guidesNot sure where to start?
Book a free 15-minute consult. We'll map your next three steps — no obligation.