Empirical Bayes Active Contrast Plot.
DESCRIPTION:
Calculates posterior probabilities that individual effects in saturated design are active and generates an active contrast plot.
USAGE: 
ebplot(x, sig=.05, method=<<see below>>,
       n.effects= <<see below>>, ...)
REQUIRED ARGUMENTS:
x:
object of class "fac.aov", from fitting fractional factorial model using fac.aov.
OPTIONAL ARGUMENTS:
sig:
value giving significance level to use for testing effects.
method:
character string giving the error used for testing if n.effects is not provided. method="mse" uses root mean squared error, "pse" uses a pseudo standard error estimate, "tse" uses a 60% trimmed standard error of the effects. "ase" uses an adaptive standard error estimate. If "mse" is available, it is the default, otherwise, "pse" is the default.
n.effects:
integer specifying number of effects thought to be important. If not provided, method is used to determine how many effects are significant.
...:
parameters passed to acplot.
DETAILS:
ebplot calls acplot after computing empirical Bayes estimates of alpha, the proportion of active effects, and k, the variance of the active effects.

If neffects is specified, based on knowledge from previous analysis graphical displays, alpha is neffects/length(feffects). If n.effects is not specified, significant effects are identified from the test based on sig and method. alpha is then estimated as the fraction of significant effects. The scale factor, k, is estimated by the square root of the F-value from the least squares model containing only the significant effects.

SIDE EFFECTS:
An empirical Bayes plot is produced on the current graphics device.
REFERENCES:
Box and Meyer (1986), An analysis for unreplicated fractional factorials, Technometrics, 28, 11-18.
SEE ALSO:
fac.aov , acplot , accalc .
EXAMPLES: 
buffer.fac <- fac.aov(buffer.df)
ebplot(buffer.fac)  # use all defaults


# specify 2 as the number of effects thought to be significant:
ebplot(buffer.fac,n.effects=2)


# use estimated standard errors to identify significant effects:
ebplot(buffer.fac,.05,'ase')
ebplot(buffer.fac,.2,'tse')