The antibody production of 12 male red-winged blackbirds before and after receiving testosterone implants was compared. The units for antibody levels were natural log (10-3 optical density) per minute (ln(mOD/min)). The mean change in antibody production was d = 0.056, and the standard deviation was sd = 0.231 If you were assigned the task of repeating this experiment and wanted to ensure that you could detect a mean change of 0.03 units with a probability of 0.8, then what sample size would you use?