evaluateGEEModel: The adaptive shrinkage estimate for generalized estimating...

In seqest: Sequential Method for Classification and Generalized Estimating Equations Problem

Description

evaluateGEEModel is used to get a generalized estimating equation of the data by the adaptive shrinkage estimate method.

Usage

evaluateGEEModel(family, corstr, y, x, clusterID, criterion = "QIC",
  theta = 0.75, gamma = 1, leastVar = 3, mostVar = ncol(x))

Arguments

family	A description of the error distribution and link function to be used in the model. See family for details of family functions.
corstr	A character string specifying the correlation structure. The following are permitted: "independence", "exchangeable" and "ar1".
y	The response data.
x	A data frame contains the covariate vectors.
clusterID	The id for each subject in the initial samples. Note that the subjects in the same cluster will have identical id.
criterion	The model selection criteria, one of the 'PWD' or 'QIC'.
theta	The parameters of the adaptive shrinkage estimate.
gamma	The parameters of the adaptive shrinkage estimate.
leastVar	The minimum number of variables.
mostVar	The maximum number of variables.

Details

evaluateGEEModel fits the current data by generalized estimating equations(GEE) according to the value of the family argument and the corstr argument. We should notice that this is not the ordinary generalized estimating equations. It can determine the variables that have an impact on the response which called effective variables. We use model selection criteria like the QIC criterion to choose the optimal value.

Value

a list containing the following components

rho	the correlation coefficient of the clusters
beta	parameters that we estimate under the current samples
sandwich	the sandwich information matrix for covariance
nonZeroIdx	the index of the non zero coefficients
call	a list containing several matrices including the sandwich matrix

seqest documentation built on July 2, 2020, 2:28 a.m.