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, statalist.org is already up and running.


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

st: RE: Randomization with ralloc


From   "Trelle Sven" <strelle@ctu.unibe.ch>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Randomization with ralloc
Date   Tue, 3 Apr 2012 14:54:21 +0200

Dear Alp,
In general, I do not see any problem with having larger randomization lists ... but anyway: I think the only possibility would be to restrict the block size to 2 (in your case with 2 treatments) i.e. set option 
	osize(1)
which is rarely appropriate (depends obviously on your situation)!
The surplus is caused by the varying block sizes (default is 5 different block sizes in ralloc e.g. with 2 treatments you will have block sizes of 2, 4, 6, 8, 10)

Alternatively, generate your randomization lists "by hand" i.e. fix the size of the 24 strata to 40 beforehand and order the sequence of your treatment within each stratum/block using random numbers (e.g. using 
function runiform()). The code for implementing varying block sizes is probably a little bit tricky (and I think you will have to determine the number of each block size beforehand for each stratum e.g. 3xblocksize==2;2xblocksize==4; 1xblocksize==6. However, the block sizes and their order might vary across strata).

Sven



-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of T. Alp Ozkan
Sent: Dienstag, 3. April 2012 14:12
To: statalist@hsphsun2.harvard.edu
Subject: st: Randomization with ralloc

Dear STATA Lister's,

I'm trying to randomize 40 patients in two groups with ralloc.

.. ralloc block size Treatment, strata (24) nsubj (40) nt (2) eq sav
(randomized)  (40 patients, 2 treatment group, 24 strata)

This results a randomization to greater than 40 patients, which is stated in help document. Is there a way to limit this randomization to
40 patients in each group?

Thanks alp
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index