PS296 Lecture Notes - Lecture 16: Sampling Distribution, Type I And Type Ii Errors, Null Hypothesis
STATISTICAL POWER:
-needed because increasing sample size can result in results that are significant, but not
meaningful
-we put the sample size back in to see if the significance is what we would expect for the
sample size
-we calculate power before running a study to determine the number of participants we need
in order to obtain a certain degree of power
Type 1 error (alpha)
-incorrectly rejecting the null hypothesis
-when a = .05, we have a 5% chance of committing a type I error
Type II error (beta)
-incorrectly failing to reject the null hypothesis
-power represents the probability of finding a significant difference when the population
means are, in fact, difference
-power is the probability of not comitting a Type II error (ex power = 1 – beta)
-power is the probability of NOT failing to reject the null hypothesis when it is “false”
-thus power is the probability of correctly concluding there is a difference between the
means
Document Summary
Needed because increasing sample size can result in results that are significant, but not meaningful. We put the sample size back in to see if the significance is what we would expect for the sample size. We calculate power before running a study to determine the number of participants we need in order to obtain a certain degree of power. When a = . 05, we have a 5% chance of committing a type i error. Power represents the probability of finding a significant difference when the population means are, in fact, difference. Power is the probability of not comitting a type ii error (ex power = 1 beta) Power is the probability of not failing to reject the null hypothesis when it is false . Thus power is the probability of correctly concluding there is a difference between the means.