2:1 allocation [General Sta­tis­tics]

posted by Helmut Homepage – Vienna, Austria, 2021-06-22 17:05 (596 d 17:31 ago) – Posting: # 22427
Views: 1,141

Hi Sundar,

welcome back to the forum!

❝ Will there be any issue in adopting 2:1 (Test:Reference) randomization method in biosimilarity (BE) studies?


You will loose some power compared to equally sized treatment arms. For an [image]-script see there. It gives for an assumed CV 40% and T/R-ratio 0.95 targeted at 80% power:

n = 130 (1:1 allocation)
  nT = nR = 65
  power = 0.8035
n = 132 (naïve 2:1 allocation)
  nT = 88, nR = 44
  power = 0.7618
n = 147 (2:1 allocation)
  nT = 98, nR = 49
  power = 0.8060

If we desire a 2:1 allocation and want to preserve power, we need 13% more subjects than for the 1:1 allocation.

❝ Note: The 2:1 randomization is mainly due to transition arm.


What do you mean by that?

Dif-tor heh smusma 🖖🏼 Довге життя Україна! [image]
Helmut Schütz
[image]

The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes

Complete thread:

UA Flag
Activity
 Admin contact
22,488 posts in 4,711 threads, 1,605 registered users;
26 visitors (0 registered, 26 guests [including 7 identified bots]).
Forum time: 09:37 CET (Europe/Vienna)

Many people tend to look at programming styles and languages like religions:
if you belong to one, you cannot belong to others.
But this analogy is another fallacy.    Niklaus Wirth

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5