Latent Class Analysis (LCA) with Familial Dependence in Extended Pedigrees

[Up] [Top]

Documentation for package ‘LCAextend’ version 1.3

Help Pages

alpha.compute computes cumulative logistic coefficients using probabilities
attrib.dens associates to a function of density parameter optimization an attribute to distinguish between ordinal and normal cases
dens.norm computes the multinormal density of a given continuous measurement vector for all classes
dens.prod.ordi computes the probability of a given discrete measurement vector for all classes under a product of multinomial
downward performs the downward step of the peeling algorithm and computes unnormalized triplet and individual weights
downward.connect performs a downward step for a connector
e.step performs the E step of the EM algorithm for a single pedigree for both cases with and without familial dependence
init.norm computes initial values for the EM algorithm in the case of continuous measurements
init.ordi computes the initial values for EM algorithm in the case of ordinal measurements
init.p.trans initializes the transition probabilities
lca.model fits latent class models for phenotypic measurements in pedigrees with or without familial dependence using an Expectation-Maximization (EM) algorithm
model.select selects a latent class model for pedigree data
n.param computes the number of parameters of a model
optim.const.ordi performs the M step for the measurement distribution parameters in multinomial case, with an ordinal constraint on the parameters
optim.diff.norm performs the M step for measurement density parameters in multinormal case
optim.equal.norm performs the M step for measurement density parameters in multinormal case
optim.gene.norm performs the M step for measurement density parameters in multinormal case
optim.indep.norm performs the M step for measurement density parameters in multinormal case
optim.noconst.ordi performs the M step for the measurement distribution parameters in multinomial case without constraint on the parameters
optim.probs performs the M step of the EM algorithm for the probability parameters
p.compute computes the probability vector using logistic coefficients
p.post.child computes the posterior probability of observations of a child
p.post.found computes the posterior probability of observations of a founder
param.cont parameters to be used for examples in the case of continuous measurements
param.ordi parameters to be used for examples in the case of discrete or ordinal measurements
ped.cont pedigrees with continuous data to be used for examples
ped.ordi pedigrees with discrete or ordinal data to be used for examples
peel peeling order of pedigrees and couples in pedigrees
probs probabilities parameters to be used for examples
upward performs the upward step of the peeling algorithm of a pedigree
upward.connect performs the upward step for a connector
weight.famdep performs the computation of triplet and individual weights for a pedigree under familial dependence
weight.nuc performs the computation of unnormalized triplet and individuals weights for a nuclear family in the pedigree