On Thu, Aug 14, 2008 at 07:46:41PM +1000, Jim Lemon wrote: > On Wed, 2008-08-13 at 19:14 -0700, Mark Home wrote: > > Dear All: > > > > I have a clinical study where I would like to compare the demographic > > information for 2 samples in a study. The demographics include both > > categorical and continuous variables. I would like to be able to say > > whether the demographics are significantly different or not. > > > > The majority of papers that I have read use multiple techniques to achieve > > this (e.g., t-test for the continuous variables and either Fischer exact or > > Chi-square for categorical). I wonder whether this might lead to spurious > > differences due to multiple significance tests. Is there a better way to > > do this? > > > Hi Mark, > Most of these comparisons are uncorrected, as the aim is to demonstrate > that the samples come from the same population. Therefore, you aren't > worried about making a Type I error, but ignoring a sampling difference > that might bias your results. > > Jim
Hi Mark, just following up on Jim's point, if your goal is to demonstrate that the samples come from the same population then you probably should take a look at equivalence testing. Andrew -- Andrew Robinson Department of Mathematics and Statistics Tel: +61-3-8344-6410 University of Melbourne, VIC 3010 Australia Fax: +61-3-8344-4599 http://www.ms.unimelb.edu.au/~andrewpr http://blogs.mbs.edu/fishing-in-the-bay/ ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
