Select.Factor {FactorCopula} | R Documentation |
A heuristic algorithm that automatically selects the bivariate parametric copula families that link the observed to the latent variables.
select1F(continuous, ordinal, count, copnamesF1, gl)
select2F(continuous, ordinal, count, copnamesF1, copnamesF2, gl)
continuous |
|
ordinal |
|
count |
|
copnamesF1 |
A vector with the names of possible candidates of bivariate copulas that link the each of the oberved variabels with the 1st factor. Choices are “bvn” for BVN, “bvt |
copnamesF2 |
A list with the names of possible candidates of bivariate copulas that link the each of the oberved variabels with the 1st and 2nd factors. Choices are “bvn” for BVN, “bvt |
gl |
Gauss legendre quardrature nodes and weights. |
The linking copulas at each factor are selected with a sequential algorithm under the initial assumption that linking copulas are Frank, and then sequentially copulas with non-tail quadrant independence are assigned to any of pairs where necessary to account for tail asymmetry (discrete data) or tail dependence (continuous data).
A list containing the following components:
“1st factor” |
The selected bivariate linking copulas for the 1st factor. |
“2nd factor” |
The selected bivariate linking copulas for the 2nd factor. |
AIC |
Akaike information criterion. |
taus |
The estimated copula parameters in Kendall's tau scale. |
Sayed H. Kadhem s.kadhem@uea.ac.uk
Aristidis K. Nikoloulopoulos a.nikoloulopoulos@uea.ac.uk
Kadhem, S.H. and Nikoloulopoulos, A.K. (2021) Factor copula models for mixed data. British Journal of Mathematical and Statistical Psychology, 74, 365–403. doi: 10.1111/bmsp.12231.
#------------------------------------------------
# Estimation
#------------------ -----------------
# Setting quadreture points
nq<-25
gl<-gauss.quad.prob(nq)
#------------------------------------------------
# PE Data
#------------------ -----------------
data(PE)
continuous.PE1 = -PE[,1]
continuous.PE <- cbind(continuous.PE1, PE[,2])
categorical.PE <- PE[, 3:5]
#------------------ One-factor -----------------
# listing the possible copula candidates:
d <- ncol(PE)
copulasF1 <- rep(list(c("bvn", "bvt3", "bvt5", "frk", "gum",
"rgum", "rjoe","joe", "1rjoe","2rjoe", "1rgum","2rgum")), d)
out1F.PE <- select1F(continuous.PE, categorical.PE,
count=NULL, copulasF1, gl)