Skip to Content

tweedie-package {tweedie}

Tweedie Distributions
Package: 
tweedie
Version: 
2.1.7

Description

Functions for computing and fitting the Tweedie family of distributions

Details

    Package: tweedie
    Type: Package
    Version: 2.1.7
    Date: 2013-01-15
    License: GPL (>=2)

References

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.          Dunn, Peter K and Smyth, Gordon K (2001).     Tweedie family densities: methods of evaluation.     Proceedings of the 16th International Workshop on Statistical Modelling,     Odense, Denmark, 2--6 July          Jorgensen, B. (1987).     Exponential dispersion models.     Journal of the Royal Statistical Society, B,     49, 127--162.          Jorgensen, B. (1997).     Theory of Dispersion Models.     Chapman and Hall, London.          Tweedie, M. C. K. (1984).     An index which distinguishes between some important exponential families.     Statistics: Applications and New Directions.     Proceedings of the Indian Statistical Institute Golden Jubilee International Conference     (Eds. J. K. Ghosh and J. Roy), pp. 579--604. Calcutta: Indian Statistical Institute.

Examples

# Generate random numbers
set.seed(987654)
y <- rtweedie( 25, xi=1.5, mu=1, phi=1)
    # With Tweedie index  xi   between 1 and 2, this produces continuous
    # data with exact zeros
x <- rnorm( length(y), 0, 1)  # Unrelated predictor
 
# With exact zeros, Tweedie index  xi  must be between 1 and 2
 
# Fit the tweedie distribution; expect  xi  about 1.5
out <- tweedie.profile( y~1, xi.vec=seq(1.1, 1.9, length=9), do.plot=TRUE)
out$xi.max
 
# Plot this distribution
tweedie.plot( seq(0, max(y), length=1000), mu=mean(y), 
              xi=out$xi.max, phi=out$phi.max)
 
# Fit the glm
require(statmod) # Provides  tweedie  family functions
summary(glm( y ~ x, family=tweedie(var.power=out$xi.max, link.power=0) ))

Author(s)

Peter K Dunn

Maintainer: Peter K Dunn

Documentation reproduced from package tweedie, version 2.1.7. License: GPL (>= 2)