BoostMLR (version 1.0.3)

updateBoostMLR: Update boosting object with an additional boosting iterations

Description

Function allows to update boosting object with an additional boosting iterations.

Usage

updateBoostMLR(Object,
               M_Add,
               Verbose = TRUE,
               ...)

Arguments

Object

Boosting object. This object is previously obtained using BoostMLR function or using update function.

M_Add

Number of additional boosting iterations.

Verbose

Print the current stage of boosting iteration?

...

Further arguments passed to or from other methods.

Details

In boosting, Mopt, the number of boosting iterations required to achive optimal result, is unknown. Typically, Mopt is estimated by specifying a large value of M and then search for an optimal value that is less than M using the test data. Function update allows user to start with a small value of M, and keep increamenting boosting iterations, each time running through the test data, until an optimal boosting iteration is found. This can significantly reduce unnecessary computations, particularly when Mopt << M. The procedure can be replicated multiple times using the boosting object (see example below). Results from update can be treated the same way we treat results from BoostMLR.

See Also

BoostMLR, predictBoostMLR, simLong

Examples

# NOT RUN {
##-----------------------------------------------------------------
## Univariate Longitudinal Response
##-----------------------------------------------------------------

# Simulate data involves 1 response and 4 covariates

dta <- simLong(n = 100, N = 5, rho =.80, model = 2, q_x = 0, 
                                  q_y = 0,type = "corCompSym")$dtaL

# Boosting call: Raw values of covariates, B-spline for time, 
# no shrinkage, no estimate of rho and phi

boost.grow <- BoostMLR(x = dta$features, tm = dta$time, id = dta$id, 
                          y = dta$y, M = 100, VarFlag = FALSE)
                          
# Update boosting object for the additional 100 iteration
boost.grow <- updateBoostMLR(Object = boost.grow, M_Add = 100,Verbose = TRUE)

# Update boosting object for the additional 50 iteration
boost.grow <- updateBoostMLR(Object = boost.grow, M_Add = 50,Verbose = TRUE)
# }