plot.proximity {randomSurvivalForest} | R Documentation |
Multidimensional scaling plot of proximity matrix.
plot.proximity(x, plot = TRUE, ...)
x |
An object of class (rsf, grow) or (rsf,
predict) . Note that proximity =TRUE must be used in
the original rsf call. |
plot |
Logical. If TRUE, proximity is plotted. |
... |
Further arguments passed to or from other methods. |
Extracts proximity information from x
and transforms this to a
symmetric proximity matrix. Dissimilarities between points are then
converted into distances using the R multidimensional scaling function
cmdscale
and then plotted. Overlayed on the plot are mortality
values, rescaled from 1-100, with 1 indicating low mortality, and 100
indicating high mortality. Mortality values will be well separated in
successful analyses. Note that points in blue correspond to events,
whereas black points are censored observations.
Invisibly, the proximity matrix with entries transformed to relative frequencies.
Hemant Ishwaran hemant.ishwaran@gmail.com and Udaya B. Kogalur ubk2101@columbia.edu
H. Ishwaran, Udaya B. Kogalur, Eugene H. Blackstone and Michael S. Lauer (2007). Random Survival Forests. Cleveland Clinic Technical Report.
rsf
,
predict.rsf
.
data(pbc, package = "randomSurvivalForest") pbc.prox.out <- rsf(Survrsf(days,status)~., pbc, ntree = 100, proximity = TRUE) plot.proximity(pbc.prox.out)