R: Control Parameters for Truncated Maximum Likelihood...
TML.noncensored.control
R Documentation
Control Parameters for Truncated Maximum Likelihood Regression
Without Censored Observations
Description
Control parameters for TML.noncensored.
Typically only used internally by TML.noncensored, but may be used to construct a control argument.
This function provides default values.
0: use and do not change the initial estimate of scale.
1: compute a truncated maximum likelihood estimate of scale.
nrep
Number of subsamples to be used in the computation of the S-estimate.
0: exhaustive sampling if the observation number is not too large.
gam
Relaxation factor for the IRLS algorithm of final estimate. Set 0 < gam <= 1.
nitmon
Set to TRUE if iteration monitoring in IRLS algorithm for the final estimate is desired. Default=FALSE.
maxit
Maximum number of iterations in IRLS algorithm for the final estimate.
tol
Relative tolerance in IRLS algorithm.
fastS
"TRUE" : the initial S-estimate is computed using lmrob.S from the
robustbase package. The control parameters are taken from lmrob.control.
"FALSE" : the initial S-estimate is computed using hysest from the
robeth package.
seed
Seed for the random number generator in the resampling algorithm for the initial S-estimate.
Value
A list with components named as the arguments.
See Also
TML.noncensored
Examples
### In the example(TML.noncensored), the control argument can be built
### using this function:
## Not run:
data(D243)
Cost <- D243$Cost # Cost (Swiss francs)
LOS <- D243$LOS # Length of stay (days)
Adm <- D243$Typadm; Adm <- (Adm==" Urg")*1 # Type of admission
# (0=on notification, 1=Emergency)
Ass <- D243$Typass; Ass <- (Ass=="P" )*1 # Type of insurance
# (0=usual, 1=private)
Age <- D243$age # Age (years)
Dst <- D243$dest; Dst <- (Dst=="DOMI")*1 # Destination
# (1=Home, 0=another hospital)
Sex <- D243$Sexe; Sex <- (Sex=="M" )*1 # Sex (1=Male, 0=Female)
# Truncated maximum likelihood regression with Gaussian errors
ctrol <- TML.noncensored.control(iv=1, nrep=0, gam=0.2, fastS=TRUE, nitmon=FALSE)
z <- TML.noncensored(log(Cost)~log(LOS)+Adm+Ass+Age+Dst+Sex, otp="adaptive")
summary(z)
## End(Not run)