A study is made to verify the effects of pesticide exposure on pupal weight of butterflies. In a pilot study, 5 randomly selected larvae are raised on plants exposed to the pesticide and their weights at pupation are calculated. Another 5 randomly selected larvae are raised on untreated plants and their weights at pupation are measured.
a. A larger study with 20 larvae in every treatment is planned. Use the pilot data to estimate the power of the larger study to detect a difference as small as 0.5 g. Assume that assumptions for a parametric test are met.
b. What is the smallest difference that could be detected with power of 0.8 and a sample size of 20 larvae in each treatment?
c. How many larvae per treatment would be needed to detect a difference of 0.5 g with power of 0.8?