Item
Universitat de Girona. Departament dâ€™InformÃ tica i MatemÃ tica Aplicada  
Ulbrich, H.F.  
2011 May 11  
Visualization of data becomes more challenging as the dimensionality of the data increases, impacting not only the display of the data itself but also the modeling results. This paper discusses common visualization techniques for compositional data. None of them seem to be well suited for changes in compositions that depend on either a metric covariate or a factor. The clrdeviation chart as a chart with a factor or covariate as abscissa and all centered log ratiotransformed component values superimposed on the ordinate axis is then introduced jointly with the clrcomponent chart. The clrdeviation chart takes advantage of the sumequalszero property of clrtransformed compositional data. It has some theoretical and practical advantages over alternatives and one major disadvantage â€“ an arbitrarily scaled ordinate axis; its properties are discussed. The usefulness of the methods are illustrated using an example analyzing the changes of proportions of the different diseases treated by hospitalization over a period of 13 years in Germany  
application/pdf  
http://hdl.handle.net/10256/13612  
eng  
Universitat de Girona. Departament dâ€™InformÃ tica i MatemÃ tica Aplicada  
CoDaWork 2011. The 4th International Workshop on Compositional Data Analysis  
Tots els drets reservats  
AnÃ lisi multivariable  Congressos
Multivariate analysis  Congresses EstadÃstica matemÃ tica  Congressos Mathematical statistics  Congresses 

Graphing and Communicating Compositional Data in High Dimensions  
info:eurepo/semantics/conferenceObject  
DUGiDocs 