glmmML.fit {glmmML} | R Documentation |
This function is called by glmmML
, but it can also be called
directly by the user.
glmmML.fit(X, Y, start.coef = NULL, start.sigma = NULL, mixed = FALSE, cluster = NULL, offset = rep(0, nobs), family = binomial(), n.points = 16, control = glm.control(), method, intercept = TRUE, boot = 0)
X |
Design matrix of covariates |
Y |
Response vector |
start.coef |
Starting values for the coefficients. |
start.sigma |
Starting value for the mixing standard deviation. |
mixed |
Logical. If FALSE, an ordinary glm is fitted. |
cluster |
The clustring variable. |
offset |
The offset in the model. |
family |
Family of distributions. Defaults to binomial with logit link. Other possibilities are binomial with cloglog link and poisson with log link. |
n.points |
Number of points in the Gauss-hermite quadrature. |
control |
Control of the iterations. See glm.control |
method |
Which optimizer? Only choice is "vmmin". |
intercept |
Logical. If TRUE, an intercept is fitted. |
boot |
Integer. If > 0, bootstrapping with boot replicates. |
"vmmin" is followed by some Newton-Raphson steps, until convergence. As a by-product we get the estimated variance-covariance matrix.
A list. For details, see the code.
A preliminary version, with high potential for bugs. However, when
it works, it is very fast, compared to glmm
and glmmPQL
Göran Broström
Broström (2003)
x <- cbind(rep(1, 14), rnorm(14)) y <- rbinom(14, prob = 0.5, size = 1) id <- rep(1:7, 2) glmmML.fit(x, y, cluster = id, mixed = TRUE, method = 1)