rcox {gRc}R Documentation

Main function for specifying RCON/RCOR models

Description

This is the main function for specifying and fitting RCON/RCOR models in the package along with certain utility functions.

Usage

rcox(gm = NULL, vcc = NULL, ecc = NULL, type = c("rcon", "rcor"),
method = c("scoring", "ipm", "matching", "user"),
fit = TRUE, data = NULL, S = NULL, n = NULL, Kstart, control = list(),
details=1, trace=0)

Arguments

gm Generating class for a grapical Gaussian model, see 'Examples' for an illustration
vcc List of vertex colour classes for the model
ecc List of edge colour classes for the model
type Type of model. Default is RCON
method Estimation method. Default is 'scoring' which is stabilised Fisher scoring. An alternative is 'ipm' which is iterative partial maximisation. The method 'matching' is score matching followed by one step with Fisher scoring. The method 'user' are for internal use and should not be called directly
fit Should the model be fitted
data A dataframe
S An empirical covariance matrix (as alternative to giving data as a dataframe)
n The number of observations (which is needed if data is specified as an empirical covariance matrix)
Kstart An initial value for K. Can be omitted.
control Controlling the fitting algorithms
details Controls the amount of output
trace Debugging info

Value

A model object of type 'RCOX'.

Note

demo("gRc-JSS") gives a more comprehensive demo.

Author(s)

Søren Højsgaard, sorenh@agrsci.dk

Examples


data(math)
gm  = ~al:an:st
vcc = list(~me+st, ~ve+an, ~al)
ecc = list(~me:ve+me:al, ~ve:al+al:st)

m1 <- rcox(gm=gm, vcc=vcc, ecc=ecc, data=math, method='matching')
m2 <- rcox(gm=gm, vcc=vcc, ecc=ecc, data=math, method='scoring')
m3 <- rcox(gm=gm, vcc=vcc, ecc=ecc, data=math, method='ipm')

m1
m2
m3

summary(m1)
summary(m2)
summary(m3)

coef(m1)
coef(m2)
coef(m3)

vcov(m1)
vcov(m2)
vcov(m3)

[Package gRc version 0.1.4 Index]