logistf.pdf {nncc}R Documentation

Likehood-ratio test of two models

Description

Please cite the original function [CLIP.confint](https://CRAN.R-project.org/package=logistf/index.html]) for publication.

Usage

logistf.pdf(
  x,
  y,
  pos,
  firth = TRUE,
  weight,
  control,
  plcontrol,
  offset = NULL,
  b,
  beta = NULL,
  loglik = NULL,
  fit = NULL,
  old = FALSE
)

Arguments

x

A model matrix returned by model.matrix

y

The response of a model frame returned by model.response

pos

Position of the variable (for which profile likelihood confidence intervals should be computed) in the colnames of model matrix x

firth

Use of Firth's penalized maximum likelihood (firth=TRUE, default) or the standard maximum likelihood method (firth=FALSE)

weight

An optional weighting variable for each observation

control

Controls Newton-Raphson iteration. Default is control= logistf.control(maxstep, maxit, maxhs, lconv, gconv, xconv)

plcontrol

Controls Newton-Raphson iteration for the estimation of the profile likelihood confidence intervals. Default is plcontrol= logistpl.control(maxstep, maxit, maxhs, lconv, xconv, ortho, pr)

offset

An optional offset variable

b

A bound for the lower or upper limit

beta

Regression coefficients for colnames of model matrix x returned by logistf

loglik

The (penalized) log-likelihood of the full models

fit

Output of logistf.fit

old

Corresponding to the legacy argument in CLIP.confint


[Package nncc version 1.0.1 Index]