Learn R Programming

studyStrap (version 1.0.0)

Study Strap and Multi-Study Learning Algorithms

Description

Implements multi-study learning algorithms such as merging, the study-specific ensemble (trained-on-observed-studies ensemble) the study strap, the covariate-matched study strap, covariate-profile similarity weighting, and stacking weights. Embedded within the 'caret' framework, this package allows for a wide range of single-study learners (e.g., neural networks, lasso, random forests). The package offers over 20 default similarity measures and allows for specification of custom similarity measures for covariate-profile similarity weighting and an accept/reject step. This implements methods described in Loewinger, Kishida, Patil, and Parmigiani. (2019) .

Copy Link

Version

Install

install.packages('studyStrap')

Monthly Downloads

147

Version

1.0.0

License

MIT + file LICENSE

Maintainer

Gabriel Loewinger

Last Published

February 20th, 2020

Functions in studyStrap (1.0.0)

fatTrim

fatTrim: Supporting function to reduce the size of models
sim.metrics

Study Strap similarity measures: Supporting function used as the default similarity measures in Study Strap, SSE, and CMSS algorithms. Compares similarity in covaraite profiles of 2 studies.
sse

Trained-on-Observed-Studies Ensemble (Study-Specific Ensemble) for Multi-Study Learning: fits one or more models on each study and ensembles models.
merged

Merged Approach for Multi-Study Learning: fits a single model on all studies merged into a single dataframe.
ss

The Study Strap for Multi-Study Learning: Fits Study Strap algorithm
studyStrap.predict

Study Strap Prediction Function: Makes predictions on object of class "ss"
cmss

Covariate-Matched Study Strap for Multi-Study Learning: Fits accept/reject algorithm based on covariate similarity measure