Countr (version 3.6.1)

predict.renewal: Predict method for renewal objects

Description

Compute predictions from renewal objects.

Usage

# S3 method for renewal
predict(
  object,
  newdata = NULL,
  type = c("response", "prob"),
  se.fit = FALSE,
  terms = NULL,
  na.action = na.pass,
  time = 1,
  ...
)

Arguments

object

Object of class inheriting from "lm"

newdata

An optional data frame in which to look for variables with which to predict. If omitted, the fitted values are used.

type

type of prediction. If equal to "response", give the mean probability associated with the individual covariates. If "prob", give the probability of the observed count.

se.fit

A switch indicating if standard errors are required.

terms

If type = "terms", which terms (default is all terms), a character vector.

na.action

function determining what should be done with missing values in newdata. The default is to predict NA.

time

TODO

...

further arguments passed to or from other methods.

Examples

fn <- system.file("extdata", "McShane_Wei_results_boot.RDS", package = "Countr")
object <- readRDS(fn)
data <- object$data
## old data
predOld.response <- predict(object, type = "response", se.fit = TRUE)
predOld.prob <- predict(object, type = "prob", se.fit = TRUE)

## newData (extracted from old Data)
newData <- head(data)
predNew.response <- predict(object, newdata = newData,
                            type = "response", se.fit = TRUE)
predNew.prob <- predict(object, newdata = newData,
                        type = "prob", se.fit = TRUE)

cbind(head(predOld.response$values),
           head(predOld.response$se$scale),
           head(predOld.response$se$shape),
           predNew.response$values,
           predNew.response$se$scale,
           predNew.response$se$shape)

cbind(head(predOld.prob$values),
      head(predOld.prob$se$scale),
      head(predOld.prob$se$shape),
      predNew.prob$values,
      predNew.prob$se$scale,
      predNew.prob$se$shape)