#21

[md90]

Power (1-B)?














Always forget this one... but it has something to do with null hypothesis..

[md90]

probability of rejecting the null hypothesis when it is false; depends on:
1. total number of endpoints experienced by population
2. difference in compliance between treatment groups (differences in the mean values between groups)
3. size of expected effect

If the sample size increases, power increases ("power in numbers"), decreases B.

[wcb22]

and remember, it's a type II error. worse than a type I error. because basically you are saying that the drug doesn't have a life threatening side effect when actually it does.

type I errors, no as bad because you are saying there is a life threatening side effect when there is not. people just don't get the drug, and pharmaceutical companies loose the money.

[md90]

thank you for making that clear for me...