meanSdPlot {vsn}R Documentation

Plot row standard deviations versus row means


Plot row standard deviations versus row means


           ranks = TRUE,
           xlab  = ifelse(ranks, "rank(mean)", "mean"),
           ylab  = "sd",
           pch   = ".",
           col, ...)


x An object of class matrix or exprSet
ranks Logical, indicating whether the x-axis (means) should be plotted on the original scale (FALSE) or on the rank scale (TRUE). The latter distributes the data more evenly along the x-axis and allows a better visual assessment of the standard deviation as a function of the mean.
xlab Character, label for the x-axis.
ylab Character, label for the y-axis.
pch Plot symbol.
col Color of plotted points. See details.
... Further arguments that get passed to plot.default.


Standard deviation and mean are calculated row-wise from the matrix exprs(x). The scatterplot of these versus each other allows to visually verify whether there is a dependence of the standard deviation (or variance) on the mean. The red dots depict the running median estimator (window-width 10%). If there is no variance-mean dependence, then the line formed by the red dots should be approximately horizontal.

If the preprocessing slot of the description slot of x is a list and contains an element named vsnTrimSelection, then the coloring of the points reflects the trimming that was used in the least trimmed sum of squares (LTS) estimation (see vsn). If the condition does not apply, and col is NULL, the points are drawn in black. If col is not NULL, its value is used for the coloring of the points.


The function is called for its side effect, creating a plot on the active graphics device.


Wolfgang Huber

See Also



  data(kidney) = function(x) log(ifelse(x>0, x, NA))

  exprs(kidney) =

  ## ...try this out with non-logged data, the lymphoma data, your data...

[Package vsn version 1.8.0 Index]