predict.flexcm: Predict method for flexible count models

In jreduardo/flexcm: Flexible Models for Dispersed Count Data

Description

Predict method for flexible count models

Usage

## S3 method for class 'flexcm'
predict(object, newdata, newmatrix = NULL,
  type = c("link", "response"), interval = c("none", "confidence"),
  level = 0.95, augment_data = FALSE, ...)

Arguments

object	a fitted object of class from "flexcm".
newdata	optionally, a data frame in which to look for variables with which to predict. If omitted, the fitted linear predictors are used.
newmatrix	optionally, a list with named design matrices ("X") used to predict. If omitted, the fitted linear predictors are used.
type	the type of prediction required. The default "link" is on the scale of the linear predictors; the alternative "response" is on the scale of the response variable (for the models that the location parameter not is the mean, it will be computed the mean by ∑ x p(x; θ)).
interval	character indicating the type of interval calculation. Currently the intervals can be "none" or "confidence".
level	level of confidence intervals.
augment_data	logical indicating if newdata should be augmented with the predict values and, possibly, confidence intervals. Default is FALSE.
...	currently not used.

Details

TODO

Value

a tibble with fitted values (column codefit) and, possibly, confidence intervals (columns lwr and upr). If augment_data, the result will be the newdata with new columns fit, fitted values, and codeste, standard errors.

Author(s)

Eduardo Jr <[e-mail]>

jreduardo/flexcm documentation built on May 8, 2019, 12:41 p.m.