The blue curve in the plot on the left is the student distribution and the red curve is the noncentral distribution. The blue vertical line is the critical value of for rejecting the null hypothesis. The noncentrality parameter, , equals . As the mean, , approaches , approaches 0 and the power of the test decreases. For a typical experimental design, is chosen in advance (normally 0.05), and the standard deviation, , cannot be controlled by the experimenter. Thus the sample size is chosen to achieve the desired power.