Skip to contents

Nearest Shrunken Centroid

Source: R/renoir_nearest_shrunken_centroid.R
renoir_nearest_shrunken_centroid.Rd

This function trains a nearest shrunken centroid classifier.

Usage

renoir_nearest_shrunken_centroid(
  x,
  y,
  weights = NULL,
  offset = NULL,
  clean,
  keep.call,
  resp.type = c("binomial", "multinomial"),
  observations = NULL,
  features = NULL,
  learning.method,
  ...,
  threshold
)

Arguments

x

the input matrix, where rows are observations and columns are variables.

y

the response variable. Its number of rows must match the number of rows of x.

weights

priors of the observations

offset

used only for GLM methods, it is an a priori known component to be included in the linear predictor during fitting

resp.type

the response type

observations

(optional) indices of observations to keep

features

(optional) indices of predictors to keep

...

further arguments to pamr.train

threshold

A vector of threshold values for the centroid shrinkage.Default is a set of 30 values chosen by the software

Value

a Trained object or a TrainedList object if learning method runs multiple configurations (i.e. multiple sets of hyper-parameters).

Results are merged into one TrainedList object

Details

Renoir interface to pamr.train.

See also

pamr.train

Author

Alessandro Barberis