mc_anova_disp: Anova Tables for dispersion components

In mcglm: Multivariate Covariance Generalized Linear Models

Anova Tables for dispersion components

Description

IT IS AN EXPERIMENTAL FUNCTION BE CAREFUL! Performs Wald tests of the significance for the dispersion components by response variables. This function is useful for joint hypothesis tests of dispersion coefficients associated with categorical covariates with more than two levels. It is not designed for model comparison.

Usage

mc_anova_disp(object, idx_list, names_list, ...)

Arguments

object	an object of class mcglm, usually, a result of a call to mcglm() function.
idx_list	list with indexes for parameter tests.
names_list	list of names to appear in the anova table.
...	additional arguments affecting the summary produced. Note that there is no extra options for mcglm object class.

Value

A data.frame with Chi-square statistic to test the null hypothesis of a parameter, or a set of parameters, be zero. Degree of freedom (Df) and p-values. The Wald test based on the observed covariance matrix of the parameters is used.

Author(s)

Wagner Hugo Bonat, [e-mail]

Examples

x1 <- seq(0, 1, l = 100)
x2 <- gl(5, 20)
beta <- c(5, 0, -2, -1, 1, 2)
X <- model.matrix(~ x1 + x2)
set.seed(123)
y <- rnorm(100, mean = 10, sd = X%*%beta)
data = data.frame("y" = y, "x1" = x1, "x2" = x2, "id" = 1)
fit.anova <- mcglm(c(y ~ 1), list(mc_dglm(~ x1 + x2, id = "id", data)),
                   control_algorithm = list(tuning = 0.9), data = data)
X <- model.matrix(~ x1 + x2, data = data)
idx <- attr(X, "assign")
idx_list <- list("idx" = idx, "idx" = idx)
names_list <- list(colnames(X), colnames(X))
mc_anova_disp(object = fit.anova, idx = idx_list, names_list = names_list)

mcglm documentation built on Sept. 16, 2022, 1:06 a.m.