predict.cubinf: Prediction methods for objects of class "cubinf"

In robcbi: Conditionally Unbiased Bounded Influence Estimates

Prediction methods for objects of class "cubinf"

Description

Predictions provided by a model fit when method is "cubinf".

Usage

## S3 method for class 'cubinf'
predict(object, newdata, type = c("link", "response", "terms"), 
   se.fit = FALSE, terms = labels(object$terms), ...)

Arguments

object	An object of class "cubinf" for which predictions are desired.
newdata	Specify the explanatory variables to used.
type	The prediction type.
se.fit	Logical to specify if standard errors are returned or not.
terms	The terms in newdata.
...	Additional arguments affecting the predictions produced.

Value

The value returned depends on type.

References

Marazzi, A. (1993). Algorithms, Routines, and S-functions for robust Statistics. Chapman and Hall, New York.

Kuensch, H.R., Stefanski L.A., Carroll R.J. (1989). Conditionally unbiased bounded-influence estimation in general regression models, with application to generalized linear models. Journal of the American Statistical Association, 84, 460-466.

See Also

predict.glm

Examples

 library(robcbi)
 data(Finney)
 Vol <- Finney$Vol; Rate <- Finney$Rate; Resp <- Finney$Resp
 df <- data.frame(lVol = log(Vol), lRate = log(Rate), Resp = Resp)
 z.cub <- glm(Resp~lVol+lRate,family=binomial,data=df,method="cubinf",ufact=3.2)
 set.seed(123)
 rVol  <- runif(20,0.4,3.7); rRate <- runif(20,0.3,3.75)
 newdat <- data.frame(lVol=log(rVol),lRate=log(rRate))
 predict(z.cub, newdat, type="response")

robcbi documentation built on Aug. 22, 2023, 1:06 a.m.