Randomised block design is more powerful than minimisation

BMJ 1999;318:263 ( 23 January )

Letters

Randomised block design is more powerful than minimisation

The first 150 words of the full text of this article appear below.

EDITOR $---$ I agree with Treasure and MacRae that the greatest determinant of the power of a study is its design.¹ Minimisationimproves power by comparing similar groups but there is a similartechnique $---$ randomised block design $---$ which has even more power.²

In this design subjects are assigned to blocks on the basis of their characteristics $---$ for example age, sex, or number of packyears smoked $---$ and then randomly allocated to a treatment groupwithin their block. In this way like is matched with like, andnot only will the mean value of each confounding factor be similarin each group but the distribution will be identical in each treatmentgroup. This means that the situation cannot arise in which twogroups have the same average age but one comprises middle agedpeople and the other comprises half younger people and half olderpeople.

The randomised block design also enables . . . [Full text of this article]

CiteULike

Complore

Connotea

Del.icio.us Add to Digg

Digg

StumbleUpon Add to Technorati

Technorati What's this?

Relevant Article

Minimisation: the platinum standard for trials?: Tom Treasure and Kenneth D MacRae
BMJ 1998 317: 362-363. [Extract] [Full Text]

This article has been cited by other articles:

Treasure, T., MacRae, K. D (1999). Minimisation is much better than the randomised block design in certain cases. BMJ 318: 1420-1420 [Full text]

Rapid Responses:

Read all Rapid Responses

Randomisation: Sue Richards
bmj.com, 4 Feb 1999 [Full text]
Minimisation and the randomised block design: Tom Treasure, et al.
bmj.com, 4 Feb 1999 [Full text]
Minimisation: the platinum standard for trials?: Vaughan Reed
bmj.com, 15 Feb 1999 [Full text]
Advantages of Minimized Block Designs: Donald R Taves
bmj.com, 5 Apr 1999 [Full text]