What is Statistical Power? Since statistical tests use data from samples to generalize an inference back to a population, errors may occur along the way. There are two major errors that can occur in hypothesis testing: Type I Error and Type II Error. A Type I Error occurs when one concludes that something (e.g., an effect or relationship) exists when, in reality, it does not (i.e., committing a false-positive); Type II Error occurs when one fails to infer a statistical relationship exists when, in reality, it does (i.e., committing a false-negative). In Psychological research, the more costly error is the Type I Error due to misdirected research time and resources. The statistical power of a study is the probability that a statistical test rejects the null hypothesis in the event that the alternative hypothesis is true. In other words, power is the likelihood of finding a statistical difference when the effect that you are testing is real [1]. There are four factors which affect the power of a test:
References [1] Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd ed). Hillsdale, N.J: L.
0 Comments
Leave a Reply. |
Categories
All
Archives
March 2021
|