1-D plot of a numeric score by density curves

This function represents a score with a density curve for each level of a factor.

Usage

s1d.density(score, fac = gl(1, NROW(score)), kernel = c("normal", "box", 
  "epanech", "biweight", "triweight"), bandwidth = NULL, gridsize = 450, 
  col = NULL, fill = TRUE, facets = NULL, plot = TRUE, storeData = TRUE,
  add = FALSE, pos = -1, ...)

Arguments

score: a numeric vector (or a data frame) used to produce the plot
fac: a factor (or a matrix of factors) to split score
kernel: the smoothing kernel used, see bkde
bandwidth: the kernel bandwidth smoothing parameter
gridsize: the number of equally spaced points at which to estimate the density
col: a logical, a color or a colors vector for labels, rugs, lines and polygons according to their factor level. Colors are recycled whether there are not one color by factor level.
fill: a logical to yield the polygons density curves filled
facets: a factor splitting score so that subsets of the data are represented on different sub-graphics
plot: a logical indicating if the graphics is displayed
storeData: a logical indicating if the data are stored in the returned object. If FALSE, only the names of the data arguments are stored
add: a logical. If TRUE, the graphic is superposed to the graphics already plotted in the current device
pos: an integer indicating the position of the environment where the data are stored, relative to the environment where the function is called. Useful only if storeData is FALSE
...: additional graphical parameters (see adegpar and trellis.par.get)

Details

kernel, bandwidth and gridsize are passed as parameters to bkde function of the KernSmooth package.

Graphical parameters for rugs are available in plines of adegpar and the ones for density curves filled in ppolygons. Some appropriated graphical parameters in p1d are also available.

Value

An object of class ADEg (subclass C1.density) or ADEgS (if add is TRUE and/or if facets or data frame for score or data frame for fac are used).
The result is displayed if plot is TRUE.

Author

Alice Julien-Laferriere, Aurelie Siberchicot aurelie.siberchicot@univ-lyon1.fr and Stephane Dray

Examples

score <- c(rnorm(1000, mean = -0.5, sd = 0.5), rnorm(1000, mean = 1))
fac <- rep(c("A", "B"), each = 1000)
s1d.density(score, fac, col = c(2, 4), p1d.reverse = TRUE)