subsemble: An Ensemble Method for Combining Subset-Specific Algorithm Fits

Share:

Subsemble is a general subset ensemble prediction method, which can be used for small, moderate, or large datasets. Subsemble partitions the full dataset into subsets of observations, fits a specified underlying algorithm on each subset, and uses a unique form of V-fold cross-validation to output a prediction function that combines the subset-specific fits. An oracle result provides a theoretical performance guarantee for Subsemble.

Author
Erin LeDell, Stephanie Sapp, Mark van der Laan
Date of publication
2014-07-01 09:37:47
Maintainer
Erin LeDell <ledell@berkeley.edu>
License
GPL (>= 2)
Version
0.0.9

View on CRAN

Man pages

predict.subsemble
Predict method for a 'subsemble' object.
subsemble
An Ensemble Method for Combining Subset-Specific Algorithm...
subsemble-package
An Ensemble Method for Combining Subset-Specific Algorithm...

Files in this package

subsemble
subsemble/NAMESPACE
subsemble/NEWS
subsemble/R
subsemble/R/subsemble.R
subsemble/R/control.R
subsemble/R/predict.subsemble.R
subsemble/R/zzz.R
subsemble/MD5
subsemble/DESCRIPTION
subsemble/man
subsemble/man/subsemble.Rd
subsemble/man/predict.subsemble.Rd
subsemble/man/subsemble-package.Rd