Publique su nota aquí (Colaborador@ Registrado)
Este es su espacio para publicar contenido, compartir experiencias, distribuir noticias, hacer comentarios sobre literatura, plantear preguntas, solicitudes de ayuda, sugerencias, apoyo a sus cursos, proyectos en marcha, recursos bibliográficos, etc, cualquier cosa sobre la Morfometría en general!

Todos puen colaborar, una vez que se han registrado. Para registrarse como "colaborador", envíe su email a la Editora.

Contenido más reciente:

24 de noviembre de 2009

Limits of Principal Components Analysis for Producing a Common Trait Space: Implications for Inferring Selection, Contingency, and Chance in Evolution

PLoS ONE: Limits of Principal Components Analysis for Producing a Common Trait Space: Implications for Inferring Selection, Contingency, and Chance in Evolution.
Comparing patterns of divergence among separate lineages or groups has posed an especially difficult challenge for biologists. Recently a new, conceptually simple methodology called the “ordered-axis plot” approach was introduced for the purpose of comparing patterns of diversity in a common morphospace. This technique involves a combination of principal components analysis (PCA) and linear regression. Given the common use of these statistics the potential for the widespread use of the ordered axis approach is high. However, there are a number of drawbacks to this approach, most notably that lineages with the greatest amount of variance will largely bias interpretations from analyses involving a common morphospace. Therefore, without meeting a set of a priori requirements regarding data structure the ordered-axis plot approach will likely produce misleading results.


Figure 1. In a common morphospace, major axes of morphological diversity may still differ among groups of interest.
Ordered axis plots may not be able to discriminate between patterns of morphological diversity along axes of a multidimensional morphospace because of its reliance upon principal components analysis and the inherent biases of this method. Here the aspects of diversity parallel to PC1 are highlighted with a red arrow for each group of interest. Note that the length of most variable group (pink) is parallel to PC1 because it has the greatest influence over the determination of PC1 in this common morphospace. Other less variable groups (blue, green) have less influence over the trajectory of PC1, but still possess variation that lies parallel to PC1. However the greatest axis of variation within these less variable groups may lie along a vector that differs from PC1. Without knowing a priori whether axes of variation among distinct groups are similar, it is impossible to know the degree to which an ordered axis plots approach will yield misleading results.


Leer el artículo completo aquí >>>

No hay comentarios:

Publicar un comentario

Publicar contenido: