a formula expression as for glm, of the form
response ~ predictors. See the documentation of lm and
formula for details. As for glm, this specifies the linear predictor
for modeling the mean. A term of the form offset(expression)
is allowed.
sformula
a formula expression of the form ~ predictor,
the response being ignored. This specifies the linear predictor for
modeling the dispersion. A term of the form
offset(expression) is allowed.
id
a vector which identifies the clusters. The length of ‘id’
should be the same as the number of observations. Data are assumed
to be sorted so that observations on a cluster are contiguous rows
for all entities in the formula.
waves
an integer vector which identifies components in
clusters. The length of waves should be the same as the
number of observation. components with the same waves value
will have the same link functions.
data
an optional data frame in which to interpret the variables occurring
in the formula, along with the id and n variables.
subset
expression saying which subset of the rows of the data should be used
in the fit. This can be a logical vector (which is replicated to have
length equal to the number of observations), or a numeric vector
indicating which observation numbers are to be included, or a
character vector of the row names to be included.
All observations are included by default.
na.action
a function to filter missing data. For gee only na.omit
should be used here.
contrasts
a list giving contrasts for some or all of the factors appearing
in the model formula. The elements of the list should have the
same name as the variable and should be either a contrast matrix
(specifically, any full-rank matrix with as many rows as there are
levels in the factor), or else a function to compute such a matrix
given the number of levels.
weights
an optional vector of weights to be used
in the fitting process. The length of weights should be the
same as the number of observations. This weights is not (yet) the
weight as in sas proc genmod, and hence is not recommended to use.
zcor
a design matrix for correlation parameters.
corp
known parameters such as coordinates used for correlation
coefficients.
control
a list of iteration and algorithmic constants. See
geese.control for their names and default
values. These can also be set as arguments to geese itself.
b
an initial estimate for the mean parameters.
alpha
an initial estimate for the correlation parameters.
gm
an initial estimate for the scale parameters.
family
a description of the error distribution and link
function to be used in the model, as for glm.
mean.link
a character string specifying the link function for
the means. The following are allowed:
"identity", "logit", "probit",
"cloglog", "log", and "inverse".
The default value is determined from family.
variance
a character string specifying the variance function
in terms of the mean. The following are allowed:
"gaussian", "binomial", "poisson", and
"gamma". The default value is determined from family.
cor.link
a character string specifying the link function for
the correlation coefficients. The following are allowed:
"identity", and "fisherz".
sca.link
a character string specifying the link function for
the scales. The following are allowed:
"identity", and "log".
link.same
a logical indicating if all the components in a
cluster should use the same link.
scale.fix
a logical variable; if true, the scale parameter is fixed at
the value of scale.value.
scale.value
numeric variable giving the value to which the scale parameter
should be fixed; used only if scale.fix == TRUE.
corstr
a character string specifying the correlation structure.
The following are permitted:
"independence",
"exchangeable",
"ar1",
"unstructured",
"userdefined", and
"fixed"
x, y
x is a design matrix of dimension n * p, and y
is a vector of observations of length n.
offset, soffset
vector of offset for the mean and for the scale, respectively.
zsca
a design matrix of dimension n * r for the scales.
...
further arguments passed to or from other methods.
Details
when the correlation structure is fixed, the specification
of Zcor should be a vector of length
sum(clusz * (clusz - 1)) / 2.