Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: RE: Measures of association for a small sample


From   Ronan Conroy <rconroy@rcsi.ie>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: RE: Measures of association for a small sample
Date   Thu, 12 Jan 2012 16:40:21 +0000

On 2012 Ean 10, at 23:48, Steve Samuels wrote:

> Your 13 regions do constitute a"population".  You can certainly compute measures of association as descriptive statistics. I don't see that statistical tests are justified unless you have a notion of a "super-population" from which the 13 regions were sampled: otherwise, what are the repetitions implied in the probability statements of type 1 error and type 2 error?. But opinions differ on this.

Such patterns as you find among the 13 regions are still worth measuring, which is one function of a measure of association.



Ronán Conroy
rconroy@rcsi.ie
Associate Professor
Division of Population Health Sciences
Royal College of Surgeons in Ireland
Beaux Lane House
Dublin 2


*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index