Review Question - QID 3131

The power of a study is an estimate of the probability of finding a significant association in a research study when one truly exists. The power is defined by 1 - probability of type-II (beta) error, and is often set at 80%. For example, a power of 80% means that if the intervention works, the study has an 80% chance of detecting this and a 20% chance of randomly missing it. A type-II or beta error occurs when one falsely concludes that there is no significant association when there actually is an association (resulting in a false-negative study that rejects a true alternative hypothesis). The type-II or beta error can be determined if Type I error rate and sample size are known. A type-I or alpha error occurs when a significant association is found when there is no true association (resulting in a false-positive study that rejects a true null hypothesis). The alpha level refers to the probability of a type-I (alpha) error and is usually set for most studies at 0.05. Answer 2 is the formula for sensitivity. Answer 3 is the formula for specificity. Answer 5 is the formula for the positive likelihood ratio. The references by Kocher and Wojtys are excellent reviews of basic biostatistic principles.