Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: random allocation three-way cross-over design

From   Steve Samuels <>
Subject   Re: st: random allocation three-way cross-over design
Date   Sat, 1 May 2010 14:19:31 -0400

There is an -ntreat()- option in -ralloc- and ntreat(3) is legal.
However -ralloc- is intended to allocate different subjects to
treatments in randomized clinical trials, not cross-over studies. DR
Cox, 1958, Planning of Experiments, Wiley, page 271, states that, if
there are no carry-over effects, the appropriate design is a 3 x 3
Latin square in which each treatment occurs equally often in each
period and each subject. When there are carry-over effects, the design
should also ensure that "each treatment follows each other treatment
the same number of times" (p. 273). I am sure that there is a more
recent literature on cross-over designs, and I suggest that you
consult it.


On Sat, May 1, 2010 at 11:42 AM, Stas Kolenikov <> wrote:
> On Sat, May 1, 2010 at 8:30 AM, Hadewijch Vandenheede
> <> wrote:
>> I wish to generate a randomization scheme for a 3-way cross-over study with
>> three treatments.
>> I'm trying to establish such scheme with 'ralloc' but it doesn't seem to
>> work out, because it can only handle 2-way cross-over designs.
>> Is there another way of doing this?
> I know very little about experiment design (although I took a couple
> of classes back in grad school 10 years ago), but I imagine that if
> you can get the complete design matrix, you can permute its rows and
> randomly assign your experimental units to these rows.
> --
> Stas Kolenikov, also found at
> Small print: I use this email account for mailing lists only.
> *
> *   For searches and help try:
> *
> *
> *

Steven Samuels
18 Cantine's Island
Saugerties NY 12477
Voice: 845-246-0774
Fax: 206-202-4783

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index