predict.BOPR: Predict new samples using a BOPR model

In haven-jeon/BOPR: Bayesian online learning scheme for probit regression with R

Description

This function produces predicted values from a BOPR model.

Usage

## S3 method for class 'BOPR'
predict(object, newdata = NULL, type = "response",
  na.action = na.pass, ...)

Arguments

object	BOPR object
newdata	a data.frame of predictors
type	either "class" for the predicted class or "prob" for model confidence values.
na.action	when using a formula for the original model fit, how should missing values be handled?
...	other options (not currently used)

Value

when type = "class", a factor vector is returned. When type = "response", probability is returned.

haven-jeon/BOPR documentation built on May 17, 2019, 3:05 p.m.