LogLikeC.Score2: Calculate the gradient of the conditional likelihood for the...

In schildjs/ods4lda: Outcome Dependent Sampling (ODS) Designs for Linear Mixed Models Data Analysis

Usage

LogLikeC.Score2(y, x, z, w.function, id, beta, sigma.vc, rho.vc, sigma.e,
  cutpoints, SampProb, Weights, CheeseCalc = FALSE)

Arguments

y	response vector
x	sum(n_i) by p design matrix for fixed effects
z	sum(n_i) by 2 design matric for random effects (intercept and slope)
w.function	sum(n_i) vector with possible values that include "mean" (mean of response series), "intercept" (intercept of the regression of Yi ~ zi where zi is the design matrix for the random effects (solve(t.zi \item idsum(n_i) vector of subject ids \item betamean model parameter p-vector \item sigma.vcvector of variance components on standard deviation scale \item rho.vcvector of correlations among the random effects. The length should be q choose 2 \item sigma.estd dev of the measurement error distribution \item cutpointsA matrix with the first dimension equal to sum(n_i). These cutpoints define the sampling regions [bivariate Q_i: each row is a vector of length 4 c(xlow, xhigh, ylow, yhigh); univariate Q_i: each row is a vector of length 2 c(k1,k2) to define the sampling regions, i.e., low, middle, high]. Each subject should have n_i rows of the same values. \item SampProbA matrix with the first dimension equal to sum(n_i). Sampling probabilities from within each region [bivariate Q_i: each row is a vector of length 2 c(central region, outlying region); univariate Q_i: each row is a vector of length 3 with sampling probabilities for each region]. Each subject should have n_i rows of the same values. \item WeightsSubject specific sampling weights. A vector of length sum(n_i). Not used unless using weighted Likelihood \item CheeseCalcIf FALSE, the function returns the gradient of the conditional log likelihood across all subjects. If TRUE, the cheese part of the sandwich esitmator is calculated.

If CheeseCalc=FALSE, gradient of conditional log likelihood. If CheeseCalc=TRUE, the cheese part of the sandwich estimator is calculated. Calculate the gradient of the conditional likelihood for the univariate and bivariate sampling cases across all subjects (CheeseCalc=FALSE) or the cheese part of the sandwich estimator if CheeseCalc=TRUE.

schildjs/ods4lda documentation built on March 16, 2020, 8:16 a.m.