Power analysis

Importance in education research Power analyses are traditionally performed as part of research design to determine the minimum sample size required to prevent committing type II errors (false negative) (Cohen, 2013). Power analyses are based on desired significance levels, effect size, and statistical power. The nested nature of large-scale datasets and variations in group representation complicate performing power analyses.

Equity issue – DBER studies do not typically include power analyses in their research design. Many underpowered equity DBER studies have assumed they had sufficient statistical power leading them to make type II errors when concluding that there are no inequities in the data.