Akaike Information Criterion for small sample size

S3 method to compute AICc (Akaike Information Criterion corrected for small sample size, see Hurvich and Tsai 1989).

Usage

AICc(object, ..., k = length(coef(object)))

Arguments

object

output of lifelihood()

...

Ignored

k

Number of estimated parameter of the modèle. Default to length(coef(object)).

Value

The AICc

See also

AIC(), BIC()

Examples

library(lifelihood)
library(tidyverse)

df <- lifelihood::fakesample |>
  mutate(
    type = as.factor(type),
    geno = as.factor(geno)
  )

clutchs <- c(
  "clutch_start1", "clutch_end1", "clutch_size1",
  "clutch_start2", "clutch_end2", "clutch_size2"
)

dataLFH <- lifelihoodData(
  df = df,
  sex = "sex",
  sex_start = "sex_start",
  sex_end = "sex_end",
  maturity_start = "mat_start",
  maturity_end = "mat_end",
  clutchs = clutchs,
  death_start = "death_start",
  death_end = "death_end",
  covariates = c("geno", "type"),
  model_specs = c("gam", "lgn", "wei")
)

results <- lifelihood(
  lifelihoodData = dataLFH,
  path_config = get_config_path("config"),
  seeds = c(1, 2, 3, 4),
  raise_estimation_warning = FALSE
)
AICc(results)
#> [1] 1624.116