statistical power

n. Statistical power is the probability of avoiding a type II error or missing a signal that is present in the data. Type II error is most likely with small sample sizes and small effect sizes. Statistical power is a serious concern for researchers because they generally want to be confident that their statistical analyses will enable them to see the trends that are present in their data. Increasing the sample size is the most common way of increasing statistical power. Psychologists have developed precise ways of calculating necessary sample size to ensure adequate statistical power. When planning a research study, psychologists often consult statistical power tables to determine the optimal sample size for detecting a trend they expect to find in their data. Power tables require researchers to estimate the magnitude of the effect they expect to find. Power tables can also be used to illustrate, post hoc, the likelihood that a type II error occurred in a given research study. By looking at the magnitude of effects and sample sizes in prior research, psychologists can determine the likelihood that an effect was missed in a given study.  – MWP

▶ See also TYPE II ERROR