Skip to content
Prev 366 / 7420 Next

help with categorical responses in boosted classification trees (gbm package)

On Fri, Oct 10, 2008 at 10:41 AM, Jill Johnstone
<jill.johnstone at usask.ca> wrote:
Are you sure that gbm is designed to handle multi-class responses
(i.e. >2 levels)?
90 observations may well not provide enough information to predict
four response levels (depending on the strengths of the relationships,
the number of observed successes, etc.)
Given the categorical response, squared error loss would not be a good
choice.  If gbm is designed to handle multi-category responses, the
'bernoulli or 'adaboost' options are more appropriate.
Have a look at the randomForest package.  Also the following Google
search may help:

boosting "multi-class" OR "k-class" OR multicategorical OR multinomial

hth,

Kingsford Jones