Check whether your planned study is large enough to detect a real effect. Under-powered studies waste effort and often miss effects that genuinely exist.
How to use it
Enter the effect size you expect (Cohen’s d), the number of participants you plan for each group, and your significance level (usually 0.05). The calculator returns your statistical power.
How to read the result
Power is the probability of detecting an effect if it is really there. The usual target is 80% or more. If your power is below that, increase the sample size, or accept a higher risk of missing a true effect.
Need a formal power calculation for ethics?
We write the power and sample-size justification your committee or funder expects. Fixed price, by email.
Frequently asked questions
What is statistical power?
It is the chance your study will find an effect that genuinely exists. Low power means a real effect can easily go undetected, so a non-significant result tells you very little.
What power should I aim for?
80% is the conventional minimum, and many funders and ethics committees expect it. Higher power (90%) needs a larger sample but reduces the risk of a false negative.
I need this for my ethics application — can you help?
Yes. We provide a formal, written power and sample-size justification tailored to your design that a committee will accept. See our sample size and power service.