Learn R Programming

fic (version 1.0.1)

Focused Information Criteria for Model Comparison

Description

Compares how well different models estimate a quantity of interest (the "focus") so that different models may be preferred for different purposes. Comparisons within any class of models fitted by maximum likelihood are supported, with shortcuts for commonly-used classes such as generalised linear models and parametric survival models. The methods originate from Claeskens and Hjort (2003) and Claeskens and Hjort (2008, ISBN:9780521852258).

Copy Link

Version

Install

install.packages('fic')

Monthly Downloads

193

Version

1.0.1

License

GPL-3

Issues

Pull Requests

Stars

Forks

Maintainer

Christopher Jackson

Last Published

March 27th, 2025

Functions in fic (1.0.1)

summary.fic

Summarise focused model comparison results
fit_submodels

Fit submodels of a general linear wide model, defined by a matrix of indicators for inclusion of covariates
plot.fic

Plot focused model comparison statistics: base graphics method
get_H0

Interpolate cumulative hazard function from a fitted Cox model
fic.survreg

Focused information criteria for parametric survival models
ggplot_fic

Plot focused model comparison statistics: ggplot2 method
newdata_to_X

Convert data frame of covariate values to a design matrix
fic_core

Focused information criteria: core calculation functions
melanoma

Malignant melanoma survival data
focus_fns

Built-in focus functions and their derivatives
all_inds.default

Form indicator matrix describing all submodels of a general linear wide model
fic.glm

Focused information criteria for generalized linear models
fic.default

Focused information criteria: main user interface
fic.flexsurvreg

Focused information criteria for flexible parametric survival models
fic.coxph

Focused information criteria for Cox proportional hazard regression models
fic.msm

Focused information criteria for multi-state models for panel data
expand_inds

Form `fic` model indicator argument in presence of factors
fic-package

Focused Information Criteria for Model Comparison
fic.lm

Focused information criteria for linear models
birthwt

Risk factors associated with low infant birth weight