Add or Drop All Possible Single Terms to a logistf Model

Share:

Description

Compute all the single terms in the scope argument that can be added to or dropped from the model, fit those models and compute a table of the changes in fit.

Usage

1
2
3
4
## S3 method for class 'logistf'
add1(object, scope, test = "PLR", ...)
## S3 method for class 'logistf'
drop1(object, scope, test = "PLR", ...)

Arguments

object

a fitted logistf object

scope

The scope of variables considered for adding or dropping. Should be a vector of variable names. Can be left missing; the method will then use all variables in the object's data slot which are not identified as the response variable.

test

The type of test statistic. Currently, only the PLR test (penalized likelihood ratio test) is allowed for logistf fits.

...

further arguments passed to or from other methods.

Details

drop1 and add1 generate a table where for each variable the penalized likelihood ratio chi-squared, the degrees of freedom, and the p-value for dropping/adding this variable are given.

Value

A matrix with nvar rows and 3 columns (Chisquared, degrees of freedom, p-value).

Author(s)

Georg Heinze

Examples

1
2
3
4
5
6
data(sex2)
fit<-logistf(data=sex2, case~1, pl=FALSE)
add1(fit)

fit2<-logistf(data=sex2, case~age+oc+dia+vic+vicl+vis)
drop1(fit2)