get_y_weight: Get outcome weights based on cross-validated super learner...

In benkeser/cvma: Cross-validation-based maximal association

Description

Get outcome weights based on cross-validated super learner fits

Usage

get_y_weight(task, Y, V, Ynames, all_fits, all_sl, all_fit_tasks,
  sl_control, y_weight_control, folds, learners)

Arguments

task	A named list identifying what training folds to use to obtain outcome weights.
Y	A matrix or data.frame of outcomes
V	Number of outer folds of cross-validation (nested cross-validation uses V-1 and V-2 folds), so must be at least four.
Ynames	Names of the columns of Y.
all_fits	A list of all learner fits (from get_fit)
all_sl	A list of all super learner fits (from get_sl)
all_fit_tasks	A list of all learner fitting tasks (quicker to search over than all_fits).
sl_control	A list with named entries ensemble.fn, optim_risk_fn, weight_fn, cv_risk_fn, family. Available functions can be viewed with sl_control_options(). See ?sl_control_options for more on how users may supply their own functions.
y_weight_control	A list with named entries ensemble.fn, optim_risk_fn, weight_fn, cv_risk_fn. Available functions can be viewed with y_weight_control_options(). See ?y_weight_control_options for more on how users may supply their own functions.
folds	Vector identifying which fold observations fall into.
learners	Super learner wrappers. See SuperLearner::listWrappers.

Value

Named list identifying training folds used and the composite outcome weights.

benkeser/cvma documentation built on May 5, 2019, 1:37 p.m.