Skip to content

Inconsistencies in the rpart.object help file?

2 messages · Terry Therneau, Tal Galili

#
This is a mistake in the help file.
that I read what it says in the help).

  For the kyphosis data set y is a factor with two levels.  For the
first split yval2 contains (1, 64, 17, .7901235, .2098765); this node is
classified into group 1, it contains 64 group 1 and 17 group 2
observations, pr(group 1) = .79 and pr(group 2) = .21.
  Note that if the model specifies priors that the last two values will
not be 64/81 and 17/81.

Terry T.