[R] conditional inference trees extracting terminal node probabilities

Steve_Friedman at nps.gov Steve_Friedman at nps.gov
Fri Jun 18 17:23:11 CEST 2010



The ctree function (package party) provides a method for running
conditional inference trees.  Plotting results of ctree returns a binary
map of the tree and for each terminal node a barplot of the probabilities
of the response categories.

For example:

 iris.ct <- ctree(Species ~ . , data = iris)
plot(iris.ct)


My dataset consists of 8 levels for a categorical response variable and I
can run the model with as many as 37 predictors.  Due to the number of
classes in the response and the number of predictors, the plot returned
compresses the barplots such that they are not interpretable,  only one
label is shown and the individual bars are not visible.

How can I extract the terminal node probabilities that are used for each of
the terminal nodes ?

Using Windows XP, R 2.11.1

Thanks
Steve


Steve Friedman Ph. D.
Spatial Statistical Analyst
Everglades and Dry Tortugas National Park
950 N Krome Ave (3rd Floor)
Homestead, Florida 33034

Steve_Friedman at nps.gov
Office (305) 224 - 4282
Fax     (305) 224 - 4147



More information about the R-help mailing list