robustbase (version 0.93-5)

residuals.glmrob: Residuals of Robust Generalized Linear Model Fits

Description

Compute residuals of a fitted glmrob model, i.e., robust generalized linear model fit.

Usage

# S3 method for glmrob
residuals(object,
          type = c("deviance", "pearson", "working",
                   "response", "partial"),
          …)

Arguments

object

an object of class glmrob, typically the result of a call to glmrob.

type

the type of residuals which should be returned. The alternatives are: "deviance" (default), "pearson", "working", "response", and "partial".

further arguments passed to or from other methods.

Details

The references in glm define the types of residuals: Davison & Snell is a good reference for the usages of each.

The partial residuals are a matrix of working residuals, with each column formed by omitting a term from the model.

The residuals (S3) method (see methods) for glmrob models has been modeled to follow closely the method for classical (non-robust) glm fitted models. Possibly, see its documentation, i.e., residuals.glm, for further details.

References

See those for the classical GLM's, glm.

See Also

glmrob for computing object, anova.glmrob; the corresponding generic functions, summary.glmrob, coef, fitted, residuals.

Examples

Run this code
# NOT RUN {
### -------- Gamma family -- data from example(glm) ---
clotting <- data.frame(
            u = c(5,10,15,20,30,40,60,80,100),
         lot1 = c(118,58,42,35,27,25,21,19,18),
         lot2 = c(69,35,26,21,18,16,13,12,12))
summary(cl <- glm   (lot1 ~ log(u), data=clotting, family=Gamma))
summary(ro <- glmrob(lot1 ~ log(u), data=clotting, family=Gamma))
clotM5.high <- within(clotting, { lot1[5] <- 60 })
cl5.high <- glm   (lot1 ~ log(u), data=clotM5.high, family=Gamma)
ro5.high <- glmrob(lot1 ~ log(u), data=clotM5.high, family=Gamma)
rr <- range(residuals(ro), residuals(cl), residuals(ro5.high))
plot(residuals(ro5.high) ~ residuals(cl5.high), xlim = rr, ylim = rr, asp = 1)
abline(0,1, col=2, lty=3)
points(residuals(ro) ~ residuals(cl), col = "gray", pch=3)

## Show all kinds of residuals:
r.types <- c("deviance", "pearson", "working", "response")
sapply(r.types, residuals, object = ro5.high)
# }

Run the code above in your browser using DataCamp Workspace