Power Flashcards
Statistical Power
The probability that the test will successfully reject a hypothesis that is false
Type I error
Rejecting the null hypothesis when it is true
Alpha
Probability of a Type I error
Type II error
Probability of not rejecting the null hypothesis when it is false
Beta
The probability of a type II error
If you make alpha smaller, you make beta…
Larger
Power is equal to…
1-Beta
(Probability of rejecting null hyp when its actually false)
Design the research experiments to…
minimize type I and type II errors simultaneously
We would like to minimize Type I errors but maximize…
Power
5 Factors that affect power of a test
- Size of alpha
- One or two tails
- Separation of HypothesizedMean and ActualMean (or the effect size, d)
- The size of population variance
- The sample size, n
A priori power calculation (G Power)
Calculating power before an experiment
Sensitivity power calculation
minimal effect size for desired power given other vairbles
G power
Free power calculation software
