Visualize Fitted Log-linear Models
Visualize fitted "loglm" objects by mosaic or
association plots.
## S3 method for class 'loglm'
plot(x, panel = mosaic, type = c("observed", "expected"),
residuals_type = c("pearson", "deviance"), gp = shading_hcl, gp_args = list(),
...)x |
a fitted |
panel |
a panel function for visualizing the observed values,
residuals and expected values. Currently, |
type |
a character string indicating whether the observed or the expected values of the table should be visualized. |
residuals_type |
a character string indicating the type of residuals to be computed. |
gp |
object of class |
gp_args |
list of arguments for the shading-generating function, if specified. |
... |
Other arguments passed to the |
The plot method for "loglm" objects by default visualizes
the model using a mosaic plot (can be changed to an association plot
by setting panel = assoc) with a shading based on the residuals
of this model. The legend also reports the corresponding p value of the
associated goodness-of-fit test. The mosaic and assoc methods
are simple convenience interfaces to this plot method, setting
the panel argument accordingly.
The "structable" visualized is returned invisibly.
Achim Zeileis Achim.Zeileis@R-project.org
library(MASS)
## mosaic display for PreSex model
data("PreSex")
fm <- loglm(~ PremaritalSex * ExtramaritalSex * (Gender + MaritalStatus),
data = aperm(PreSex, c(3, 2, 4, 1)))
fm
## visualize Pearson statistic
plot(fm, split_vertical = TRUE)
## visualize LR statistic
plot(fm, split_vertical = TRUE, residuals_type = "deviance")
## conditional independence in UCB admissions data
data("UCBAdmissions")
fm <- loglm(~ Dept * (Gender + Admit), data = aperm(UCBAdmissions))
## use mosaic display
plot(fm, labeling_args = list(abbreviate = c(Admit = 3)))
## and association plot
plot(fm, panel = assoc)
assoc(fm)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.