Factors Affecting Power: Size of the Difference between Population Means (3 of 3)
Next section: Significance level
The experimenter usually has little control over the size of the effect
although sometimes the experimenter can choose the
levels of the
independent variable to increase
the size of the effect. For instance, the size of the effect may be greater
when a 500 mg dose is compared to a placebo then when a 300 mg dose is compared.
Naturally researchers hope that the variables they manipulate have large
effects. When they do not, the power of their experiments is generally low.
Next section: Significance level