Title A method for visual identification of small sample subgroups and potential biomarkers
Authors Charlotte Soneson, Magnus Fontes
Alternative Location http://dx.doi.org/10.1214/1..., Restricted Access
Publication The Annals of Applied Statistics
Year 2011
Volume 5
Issue 3
Pages 2131 - 2149
Document type Article
Status Published
Quality controlled Yes
Language eng
Publisher Institute of Mathematical Statistics
Abstract English In order to find previously unknown subgroups in biomedical data and <br> generate testable hypotheses, visually guided exploratory analysis can be of <br> tremendous importance. In this paper we propose a new dissimilarity measure <br> that can be used within the Multidimensional Scaling framework to obtain a <br> joint low-dimensional representation of both the samples and variables of a <br> multivariate data set, thereby providing an alternative to conventional biplots. <br> In comparison with biplots, the representations obtained by our approach are <br> particularly useful for exploratory analysis of data sets where there are small <br> groups of variables sharing unusually high or low values for a small group of <br> samples.
ISBN/ISSN/Other ISSN: 1941-7330 (online)

Questions: webmaster
Last update: 2013-04-11

Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Telefon: +46 46-222 00 00 (vx)