I am reading that generally, the 50/50 split leads of control/ treatment to the highest statistical power, but If I found less proportion of control group like 20/80, the power of study will be affected or not. I mean what is the lowest cut off proportion split keeps an acceptable statistical power? like 30/70 or 35/ 65 or 40/60.

More Mohamed A. Hammad's questions See All
Similar questions and discussions