[R] mboost: Proportional odds boosting model - how to specify the offset?

Nussbaum Madlene madlene.nussbaum at env.ethz.ch
Fri Mar 13 14:17:58 CET 2015

Dear R team

The package mboost allows for boosting of proportional odds models. 
However, I would like to include an offset for every observation. This 
produces an error - no matter how I put the offset (as response 
probabilities or as response link).

Fitting gamboost-models with offset works satisfactory with family = 
Gaussian() or Multinomial().

1) How do I need to specify the offset with family = PropOdds()?

2) Where in the mboost-object do I find the Theta's (response category 
dependent intercept)?

# --- minimal example with iris data ---


iris$Species <- factor(iris$Species, ordered = T)
p.iris <- polr(Species  ~ Sepal.Length, data = iris)
mlp <- gamboost(Species ~ bols(Sepal.Length) + bols(Sepal.Width),
               data = iris, family = PropOdds(),
	      offset = fitted(p.iris) )

Error in tmp[[i]] : subscript out of bounds

Thank you
M. Nussbaum


ETH Zürich
Madlene Nussbaum
Institut für Terrestrische Ökosysteme
Boden- und Terrestrische Umweltphysik
CHN E 37.2
Universitätstrasse 16
CH-8092 Zürich

Telefon + 44 632 73 21
Mobile  + 79 761 34 66

madlene.nussbaum at env.ethz.ch

More information about the R-help mailing list