Consider the process of planning for adequate power when designing an experiment for which a two-sample t test will be used.
(a) Suppose the effect size is constant and the chosen alpha level is also constant (a) (e.g., at 0.05). If the sample sizes for the two groups go up from 12 to 18, how does this affect power? That is, does power go down, stay the same, or go up? Why? How is this related to the standard error?
(b) The graph below shows two normally distributed populations. Calculate the effect size here.