AICtweedie {tweedie} | R Documentation |
The AIC for Tweedie models
AICtweedie( glm.obj, k = 2)
glm.obj |
a fitted Tweedie |
k |
numeric: the penalty per parameter to be used; the default is k=2 |
See AIC
for more details on the AIC;
see link{dtweedie}
for ore details on computing the Tweedie densities
Returns a numeric value with the corresponding AIC (or BIC, depending on k)
Computing the AIC can take a long time!
Peter Dunn (pdunn2@usc.edu.au)
Dunn, P. K. and Smyth, G. K. (2008). Evaluation of Tweedie exponential dispersion model densities by Fourier inversion. Statistics and Computing, 18, 73–86.
Dunn, Peter K and Smyth, Gordon K (2005). Series evaluation of Tweedie exponential dispersion model densities Statistics and Computing, 15(4). 267–280.
Jorgensen, B. (1997). Theory of Dispersion Models. Chapman and Hall, London.
Sakamoto, Y., Ishiguro, M., and Kitagawa G. (1986). Akaike Information Criterion Statistics. D. Reidel Publishing Company.
library(statmod) # Needed to use tweedie family object ### Generate some fictitious data test.data <- rgamma(n=200, scale=1, shape=1) ### Fit a Tweedie glm and find the AIC m1 <- glm( test.data~1, family=tweedie(link.power=0, var.power=2) ) ### A Tweedie glm with p=2 is equivalent to a gamma glm: m2 <- glm( test.data~1, family=Gamma(link=log)) ### The models are equivalent, so the AIC shoud be the same: AICtweedie(m1) AIC(m2)