The Standard Biplot

Biplots are graphical displays of data matrices based on the decomposition of a matrix as the product of two matrices. Elements of these two matrices are used as coordinates for the rows and columns of the data matrix, with an interpretation of the joint presentation that relies on the properties of the scalar product. Because the decomposition is not unique, there are several alternative ways to scale the row and column points of the biplot, which can cause confusion amongst users, especially when software packages are not united in their approach to this issue. We propose a new scaling of the solution, called the standard biplot, which applies equally well to a wide variety of analyses such as correspondence analysis, principal component analysis, log-ratio analysis and the graphical results of a discriminant analysis/MANOVA, in fact to any method based on the singular-value decomposition. The standard biplot also handles data matrices with widely different levels of inherent variance. Two concepts taken from correspondence analysis are important to this idea: the weighting of row and column points, and the contributions made by the points to the solution. In the standard biplot one set of points, usually the rows of the data matrix, optimally represent the positions of the cases or sample units, which are weighted and usually standardized in some way unless the matrix contains values that are comparable in their raw form. The other set of points, usually the columns, is represented in accordance with their contributions to the low-dimensional solution. As for any biplot, the projections of the row points onto vectors defined by the column points approximate the centred and (optionally) standardized data. The method is illustrated with several examples to demonstrate how the standard biplot copes in different situations to give a joint map which needs only one common scale on the principal axes, thus avoiding the problem of enlarging or contracting the scale of one set of points to make the biplot readable. The proposal also solves the problem in correspondence analysis of low-frequency categories that are located on the periphery of the map, giving the false impression that they are important.

Contribution biplots

In order to interpret the biplot it is necessary to know which points usually variables are the ones that are important contributors to the solution, and this information is available separately as part of the biplot s numerical results. We propose a new scaling of the display, called the contribution biplot, which incorporates this diagnostic directly into the graphical display, showing visually the important contributors and thus facilitating the biplot interpretation and often simplifying the graphical representation considerably. The contribution biplot can be applied to a wide variety of analyses such as correspondence analysis, principal component analysis, log-ratio analysis and the graphical results of a discriminant analysis/MANOVA, in fact to any method based on the singular-value decomposition. In the contribution biplot one set of points, usually the rows of the data matrix, optimally represent the spatial positions of the cases or sample units, according to some distance measure that usually incorporates some form of standardization unless all data are comparable in scale. The other set of points, usually the columns, is represented by vectors that are related to their contributions to the low-dimensional solution. A fringe benefit is that usually only one common scale for row and column points is needed on the principal axes, thus avoiding the problem of enlarging or contracting the scale of one set of points to make the biplot legible. Furthermore, this version of the biplot also solves the problem in correspondence analysis of low-frequency categories that are located on the periphery of the map, giving the false impression that they are important, when they are in fact contributing minimally to the solution.

Caracterización morfológica del M2 de Primates Hominoidea a partir de análisis de Fourier

Los análisis de Fourier permiten caracterizar el contorno del diente a partir de un número determinado de puntos y extraer una serie de parámetros para un posterior análisis multivariante. No obstante, la gran complejidad que presentan algunas conformaciones, obliga a comprobar cuántos puntos son necesarios para una correcta representación de ésta. El objetivo de este trabajo es aplicar y validar los análisis de Fourier (Polar y Elíptico) en el estudio de la forma dental a partir de diferentes puntos de contorno y explorar la variabilidad morfométrica en diferentes géneros. Se obtuvieron fotografías digitales de la superfi cie oclusal en segundos molares inferiores (M2s) de 4 especies de Primates (Hylobates moloch, Gorilla beringei graueri, Pongo pygmaeus pygmaeus y Pan troglodytes schweirfurthii) y se defi nió su contorno con 30, 40, 60, 80, 100 y 120 puntos y su representación formal a 10 armónicos. El análisis de la variabilidad morfométrica se realizó mediante la aplicación de Análisis Discriminantes y un NP-MANOVA a partir de matrices de distancias para determinar la variabilidad y porcentajes de clasifi cacióncorrecta, a nivel metodológico y taxonómico. Los resultados indicaron que los análisis de forma con series de Fourier permiten analizar la variabilidad morfométrica de M2s en géneros de Hominoidea, con independencia del número de puntos de contorno (30 a 120). Los porcentajes de clasifi cación son más variables e inferiores con el uso de la serie Polar (≈60-90) que con la Elíptica (75-100%). Un número entre 60-100 puntos de contorno mediante el método elíptico garantiza una descripción correcta de la forma del diente.