sgdGMF (version 1.0)

cpp.airwls.update: AIRWLS update for GMF models

Description

Internal function implementing one step of AIRWLS for the estimation of GMF models.

Usage

cpp.airwls.update(
  beta,
  Y,
  X,
  familyname,
  linkname,
  varfname,
  idx,
  offset,
  weights,
  penalty,
  transp = FALSE,
  nsteps = 100L,
  stepsize = 0.1,
  print = FALSE,
  parallel = FALSE,
  nthreads = 1L
)

Arguments

beta

initial value of the regression coefficients to be estimated

Y

response vector

X

design matrix

familyname

model family name

linkname

link function name

varfname

variance function name

idx

index identifying the parameters to be updated in beta

offset

vector of constants to be added to the linear predictor

weights

vector of constants non-negative weights

penalty

penalty parameter of a ridge-type penalty

transp

if TRUE, transpose the data

nsteps

number of iterations

stepsize

stepsize parameter of the Fisher scoring algorithm

print

if TRUE, print the algorithm history

parallel

if TRUE, run the updates in parallel using openMP

nthreads

number of threads to be run in parallel (only if parallel=TRUE)