Sample size calculation
Let us now return to the different options proposed earlier.
Option 3. Continue the experiment but exclude diet A+D altogether and assign the 12 goats equally to diets C and B. This option allows 12 goats to be compared on diets C and B.
Comment: The analysis of data collected in the first two batches indicates that there is little difference in milk yields between goats fed diet B or C. So, again how much improvement would this be on Option 1?
Option
|
Groups
|
|
|
C
|
A + D
|
B
|
A + B
|
1
|
9 (1,2,3)*
|
6 (3)
|
9 (1,2,3)
|
0
|
2
|
10 (1,2,3,4)
|
10 (3,4)
|
10 (1,2,3,4)
|
0
|
3
|
12 (1,2,3)
|
0
|
12 (1,2,3)
|
0
|
4
|
10 (1,2,3)
|
0
|
10 (1,2,3)
|
10 (1,2,3)
|
* batch numbers in which goats occur
|