visAFCM: visAFCM: this function plots multiple correspondence analysis graphs based on ade4 package functions.

Description

Plots multiple correspondence analysis graphs. The graphs can be unique or multiple which is sometimes necessary for better lisibility.

Usage

visAFCM(data, scannf=FALSE, nf=2, xax = 1, yax = 2, clab.row = FALSE, clab.col = 1,
  permute = FALSE, posieig = "top", sub = NULL, graphstyle = "unique",
  graphrow = 1, graphcol = 3, cpoint = 1, clabel = 2, csub = 2)

Arguments

data: A data.frame with the qualitative variables which should be taken in account in the multiple correspondence analysis.
scannf: A logical value indicating whether the eigenvalues bar plot should be displayed; see ade4 package (by default scannf = FALSE).
nf: If scannf=FALSE, an integer indicating the number of kept axes; see ade4 package (by default nf = 2).
xax: A numeric giving the number of the first axis to plot (by default xax = 1).
yax: A numeric giving the number of the second axis to plot (by default yax = 2).
clab.row: A character size for the rows (by default clab.row = FALSE).
clab.col: A character size for the columns (by default clab.col = 1).
permute: If FALSE, the rows are plotted by points and the columns by arrows. If TRUE it is the opposite (by default permute = FALSE).
posieig: If "top" the eigenvalues bar plot is upside, if "bottom" it is downside, if "none" no plot. "topleft" and "bottomleft" are also possible (by default posieig = "top").
sub: A string of characters to be inserted as legend (by default sub = NULL).
graphstyle: Three kinds of graph can be selected. If graphstyle = "unique", all variables will be plotted on the same graph. If graphstyle = "multiple a" each variable will be plotted in different graphs (cf. graphrow and graphcol) with inertia ellipse. If graphstyle = "multiple b" each variable will be plotted in different graphs (cf. graphrow and graphcol) with convex hulls.
graphrow: The number of row for multiple graph. If one deal with 6 variables it is recommended to write graphrow = 2 and graphcol = 3.
graphcol: The number of column for multiple graph. If one deal with 6 variables it is recommended to write graphrow = 2 and graphcol = 3.
cpoint: A numeric for the size of the points.
clabel: A numeric for the size of the labels.
csub: A numeric for the size of the name of the variable written at the bottom of each chart.

Author

Borel A., Pouydebat E., Reghem E. <antony.borel@gmail.com> based on functions from Daniel Chessel, Anne-Beatrice Dufour and Stephane Dray, with contributions from Thibaut Jombart, Jean R. Lobry, Sebastien Ollier, Sandrine Pavoine and Jean Thioulouse. Package ade4: Analysis of Ecological Data : Exploratory and Euclidean methods in Environmental sciences.

References

Daniel Chessel, Anne-Beatrice Dufour and Stephane Dray, with contributions from Thibaut Jombart, Jean R. Lobry, Sebastien Ollier, Sandrine Pavoine and Jean Thioulouse. Package ade4: Analysis of Ecological Data : Exploratory and Euclidean methods in Environmental sciences.

Examples

Run this code

  data(laterdata)
  ## "unique" graph:
  visAFCM(laterdata)
  
  ## "multiple a" graph:
  visAFCM(laterdata, xax = 1, yax = 2, clab.row = FALSE, clab.col = 1,
  permute = FALSE, posieig = "top", sub = NULL, graphstyle = "multiple a",
  graphrow = 2, graphcol = 3, cpoint=3)
  
  ## "multiple b" graph:
  visAFCM(laterdata, xax = 1, yax = 2, clab.row = FALSE, clab.col = 1,
  permute = FALSE, posieig = "top", sub = NULL, graphstyle = "multiple b",
  graphrow = 2, graphcol = 3)