Prediction intervals with tidymodels, best practices?

brshallo · September 29, 2020, 3:04pm

Thanks for the reply and the link! I did check here but seemed to only be for parametric approach and also seemed to only be for linear models:

github.com

tidymodels/tidypredict/blob/main/R/predict-interval.R

#' Returns a Tidy Eval formula to calculate prediction interval.
#'
#' It parses a model or uses an already parsed model to return a
#' Tidy Eval formula that can then be used inside a dplyr command.
#'
#' The result still has to be added to and subtracted from the fit to obtain the upper and
#' lower bound respectively.
#'
#' @param model An R model or a list with a parsed model
#' @param interval The prediction interval, defaults to 0.95
#'
#' @examples
#'
#' model <- lm(mpg ~ wt + cyl * disp, offset = am, data = mtcars)
#' tidypredict_interval(model)
#' @export
tidypredict_interval <- function(model, interval = 0.95) {
  UseMethod("tidypredict_interval")
}

This file has been truncated. show original

(Scrolling to bottom)

I would be interested in an example that uses simulation based approach as well as example for non-linear model.