mpcmp (version 0.3.6)

regression.diagnostic.cmp: CMP Regression Diagnostic

Description

This suite of functions provides the basic quantities which are used in forming a wide variety of diagnostics for checking the quality of regression fits.

Usage

# S3 method for cmp
influence(model, ...)
# S3 method for cmp
hatvalues(model, ...)
# S3 method for cmp
rstandard(
  model,
  infl = influence.cmp(model),
  type = c("deviance", "pearson"),
  ...
)
# S3 method for cmp
cooks.distance(
  model,
  infl = influence(model),
  res = infl$pear_res,
  hat = infl$hat,
  ...
)

Arguments

model

an object class 'cmp', obtained from a call to glm.cmp.

...

other arguments passed to or from other methods (currently unused).

infl

influence structure as returned by influence, only for rstudent and cooks.distance.

type

type of residuals for rstandard. The alternatives are: 'deviance' (default), and 'pearson'.

res

residuals, with proper default.

hat

hat values \(H[i,i]\), see default.

Examples

# NOT RUN {
data(attendance)
M.attendance <- glm.cmp(daysabs~ gender+math+prog, data=attendance)
influence(M.attendance)
hatvalues(M.attendance)
rstandard(M.attendance, type = "pearson")
cooks.distance(M.attendance)
# }