rcox {gRc} | R Documentation |
This is the main function for specifying and fitting RCON/RCOR models in the package along with certain utility functions.
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)
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 |
A model object of type 'RCOX'.
demo("gRc-JSS") gives a more comprehensive demo.
Søren Højsgaard, sorenh@agrsci.dk
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)