rcox function

Main function for specifying RCON/RCOR models.

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 = "ipm",
  fit = TRUE,
  data = NULL,
  S = NULL,
  n = NULL,
  Kstart = NULL,
  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; see 'Details' below.
• 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

Returns

A model object of type 'RCOX'.

Details

Estimation methods:

• 'ipm' (default) is iterative partial maximization which when finished calculates the information matrix so that approximate variances of the parameters can be obtained using vcov().

• 'ipms' is iterative partial maximization without calculating the information matrix. This is the fastest method.

• 'scoring' is stabilised Fisher scoring.

• 'matching' is score matching followed by one step with Fisher scoring.

• 'hybrid1' is for internal use and should not be called directly

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)

Author(s)

Søren Højsgaard, sorenh@math.aau.dk