train_CFA: Train a copula FA model

In gregorp90/RStan-package-test: Copula-Based Factor Analysis

Description

This function trains a copula factor analysis model in Stan.

Usage

train_CFA(train, gp_train, nfac = 2, ...)

Arguments

train	data frame. The training data set, consisting of counts. Columns represent variables, rows represent observations.
gp_train	vector. Groups for each observation.
nfac	numeric. The number of factors.
...	Arguments passed to rstan::sampling (e.g. iter, chains).

Details

The transformations are made separately, between the modeling of marginals and the correlation.

Value

A list.

train	Training data set.
gp_train	A vector of groups for each observation.
loadings	Aggregated loadings.
scores	Aggregated factor scores.
noise	Aggregated residual covariance matrix.
noise_org	Aggregated residual covariance matrix, scaled by the variance of the original data.
Sigma	Aggregated correlation matrix.
stan_mod	A list with two elements. Both are objects of S4 class stanfit. First is the marginal distribution estimation, second is the copula.

gregorp90/RStan-package-test documentation built on May 26, 2019, 1:32 a.m.