Power analysis

Question 1

Power

Answer 1

• Ability to detect an effect if there is one
  
  • The probability of not committing a Type II error = 1 - beta where beta is the probability of a type II error
  • By convention, power should be .80=80% chance of detecting an effect if there is one

Question 2

Influences on power

Answer 2

• Effect size: larger effects are easier to detect
• Alpha-level: strictness of our significance criterion (e.g. p<.05 or p<.01)
• Sample size: larger samples are more like population → less error, more power

⇒ Knowing effect size, alpha-level and power, we can determine the required sample size for our experiment - use a program