errorBarGraph.cgOneFactorFit {cg} | R Documentation |
Create an Error Bar graph amongst groups in a cgOneFactorFit object
Description
Creates a graph to see comparisons amongst groups based on the cgOneFactorFit object. The method of Andrews, Sarner, and Snee (1980) is applied to visualizes significant differences via non-overlapping error bars.
Usage
## S4 method for signature 'cgOneFactorFit'
errorBarGraph(fit, mcadjust = FALSE, alpha =0.05,
cgtheme = TRUE, device = "single", ...)
Arguments
fit |
A fit object of class |
mcadjust |
Do a multiple comparisons adjustment, based on the simultaneous
inference capabilities of the multcomp package. See Details
below. The default value is |
alpha |
Significance level, by default set to |
cgtheme |
When set to the default |
device |
Can be one of three values:
|
... |
Additional arguments. Two are currently valid:
|
Details
When mcadjust=TRUE
, a status message of
"Some time may be needed as the critical point"
"from the multcomp::summary.glht function call is calculated"
is displayed at the console. This computed critical point
is used for all interval calculations.
The multcomp package provides a unified way to calculate critical points based on the comparisons of interest in a "family". Thus a user does not need to worry about choosing amongst the myriad names of multiple comparison procedures.
The errorBarGraph.cgOneFactorFit
method is only relevant for
classical least squares and resistant & robust fits in the
cgOneFactorFit
object. There is an
errorbargraph
core function that could be used for
approximations in other cases like accelerated failure time or unequal
variance fits.
The statistical method of Andrews, Sarner, and Snee (1980) is applied to visualize significant differences via non-overlapping error bars. The method is exact when there are equal sample sizes amongst the groups for the classical least squares case. When there are unequal group sample sizes or a resistant & robust fit is used to create the graph, the method is approximate, and this is noted in the main title section of the graph. For the unequal sample sizes, the harmonic mean is calculated to use for all the groups. The method's usefulness declines as the sample sizes become more disparate.
When two groups are compared, nonoverlapping error bars indicate a
statistically significant pairwise difference. Conversely, if the
error bars overlap, there is no such significant difference. In cases
of approximation, or borderline overlap that is seen, the
cgOneFactorComparisonsTable
object created with
type="pairwisereflect"
or type="pairwise"
needs to be
consulted to judge significance with a p-value.
The minimum and maximum values across all the bar ends
are added inside the plot region in blue, flush against the
y-axis. The number of decimal places are determined by the
digits
value in the fit$settings
slot.
If group labels along the x-axis seem to overlap in the standard horizontal form, they will be rotated 45 degrees.
Value
errorBarGraph.cgOneFactorFit
returns
an invisible NULL
. The main purpose is the side
effect of graphing to the current device.
Note
Contact cg@billpikounis.net for bug reports, questions, concerns, and comments.
Author(s)
Bill Pikounis [aut, cre, cph], John Oleynick [aut], Eva Ye [ctb]
References
Andrews, H.P., Snee, R.D., Sarner, M.H. (1980). "Graphical Display of Means," The American Statistician, 34, 195-199.
Hothorn, T., Bretz, F., Westfall, P., Heiberger, R.M., and
Schuetzenmeister, A. (2010). The multcomp
R package.
Hothorn, T., Bretz, F., and Westfall, P. (2008). "Simultaneous Inference in General Parametric Models", Biometrical Journal, 50, 3, 346-363.
Examples
data(canine)
canine.data <- prepareCGOneFactorData(canine, format="groupcolumns",
analysisname="Canine",
endptname="Prostate Volume",
endptunits=expression(plain(cm)^3),
digits=1, logscale=TRUE, refgrp="CC")
canine.fit <- fit(canine.data)
errorBarGraph(canine.fit)
errorBarGraph(canine.fit, mcadjust=TRUE, model="olsonly")