glmtoolbox: anova.overglm – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

anova.overglm

Comparison of nested Negative Binomial and Beta-Binomial Regression Models

Description

Allows to compare nested negative binomial and beta-binomial regression models using Wald, score, gradient and likelihood ratio tests.

Usage

## S3 method for class 'overglm'
anova(
  object,
  ...,
  test = c("wald", "lrt", "score", "gradient"),
  verbose = TRUE
)

Arguments

`object`	an object of the class overglm which is obtained from the fit of a negative binomial or beta-binomial model.
`...`	another objects of the class overglm which are obtained from the fit of negative binomial or beta-binomial models.
`test`	an (optional) character string indicating the required test. The available options are: Wald ("wald"), Rao's score ("score"), likelihood ratio ("lrt") and Terrell's gradient ("gradient") tests. By default, `test` is set to be "wald".
`verbose`	an (optional) logical indicating if should the report of results be printed. By default, `verbose` is set to be TRUE.

Details

The Wald, Rao's score and Terrell's gradient tests are performed using the observed Fisher information matrix.

Value

A matrix with three columns which contains the following:

Chi: The value of the statistic of the test.
Df: The number of degrees of freedom.
Pr(>Chi): The p-value of the test computed using the Chi-square distribution.

References

Buse A. (1982) The Likelihood Ratio, Wald, and Lagrange Multiplier Tests: An Expository Note. The American Statistician 36, 153 - 157.

Terrell G.R. (2002) The gradient statistic. Computing Science and Statistics 34, 206 – 215.

Examples

## Example 1
fit1 <- overglm(cbind(cells,200-cells) ~ tnf, family="bb(logit)", data=cellular)
fit2 <- update(fit1, . ~ . + ifn)
fit3 <- update(fit2, . ~ . + tnf:ifn)
anova(fit1, fit2, fit3, test="wald")
anova(fit1, fit2, fit3, test="score")
anova(fit1, fit2, fit3, test="lrt")
anova(fit1, fit2, fit3, test="gradient")

## Example 2
fit1 <- overglm(infections ~ frequency, family="nb1(log)", data=swimmers)
fit2 <- update(fit1, . ~ . + location)
fit3 <- update(fit2, . ~ . + age)
fit4 <- update(fit3, . ~ . + gender)
anova(fit1, fit2, fit3, fit4, test="wald")
anova(fit1, fit2, fit3, fit4, test="score")
anova(fit1, fit2, fit3, fit4, test="lrt")
anova(fit1, fit2, fit3, fit4, test="gradient")

glmtoolbox

Set of Tools to Data Analysis using Generalized Linear Models

v0.1.0

GPL-2 | GPL-3

Authors

Luis Hernando Vanegas [aut, cre], Luz Marina Rondón [aut], Gilberto A. Paula [aut]

Initial release