Many tests for the dispersion parameter in Poisson distribution {Rfast}

Many tests for the dispersion parameter in Poisson distribution

Description

Many tests for the dispersion parameter in Poisson distribution.

Usage

colpoisdisp.tests(y, alternative = "either", logged = FALSE)
colpois.tests(y, logged = FALSE)

Arguments

y

A numerical matrix with count data, 0, 1,...

alternative

Do you want to test specifically for either over or underspirsion ("either"), overdispersion ("over") or undersispersion ("under")?

logged

Set to TRUE if you want the logarithm of the p-value.

Value

A matrix with two columns, the test statistic and the (logged) p-value.

Author(s)

Michail Tsagris

R implementation and documentation: Michail Tsagris <[e-mail]> and Manos Papadakis <[e-mail]>.

References

Yang Zhao, James W. Hardin, and Cheryl L. Addy. (2009). A score test for overdispersion in Poisson regression based on the generalized Poisson-2 model. Journal of statistical planning and inference 139(4):1514-1521.

Dimitris Karlis and Evdokia Xekalaki (2000). A Simulation Comparison of Several Procedures for Testing the Poisson Assumption. Journal of the Royal Statistical Society. Series D (The Statistician), 49(3): 355-382.

Bohning, D., Dietz, E., Schaub, R., Schlattmann, P. and Lindsay, B. (1994) The distribution of the likelihood ratio for mixtures of densities from the one-parameter exponential family. Annals of the Institute of Statistical Mathematics, 46(): 373-388.

See Also

poisson.mle, negbin.mle, poisson.anova, poisson.anovas, poisson_only

Examples

y <- matrix(rnbinom(100* 50, 10, 0.6), ncol = 50)
a1 <- colpoisdisp.tests(y, "over")
b1 <- colpois.tests(y)

y <- matrix(rpois(100* 50, 10), ncol = 50)
a2 <- colpoisdisp.tests(y, "either")
b2 <- colpois.tests(y)
y <- NULL