predict function

Prediction Methods for robustbetareg Objects Class

Extract various types of predictions from beta regression models: either on the scale of responses in (0, 1) or the scale of the linear predictor, from robustbetareg objects.

predict(
  object,
  newdata = NULL,
  type = c("response", "link", "precision", "variance", "quantile"),
  at = 0.5,
  ...
)

Arguments

• object: fitted model object of class "robustbetareg".
• newdata: optional, a data frame with new predictor values. If omitted, the original predictors are used.
• type: character indicating type of predictions: fitted means of response ("response"), corresponding linear predictor ("link"), fitted precision parameter phi ("precision"), fitted variances of response ("variance"), or fitted quantile(s) of the response distribution ("quantile").
• at: numeric vector indicating the level(s) at which quantiles should be predicted (only if type = "quantile"). Default is the median at = 0.5.
• ...: currently not used.

Returns

Return a vector with the predicted values.

Examples

get(data("HIC", package = "robustbetareg"))
hic <- robustbetareg(HIC ~ URB + GDP | 1, data = HIC, alpha = 0.04)
cbind(predict(hic, type = "response"), predict(hic, type = "quantile", at = c(0.25, 0.5, 0.75)))