KStepNewtonMove: Newton move for spline models without dimession changes.

In feng-li/movingknots: Efficient Bayesian multivariate surface regression

Description

Details see the paper.

Usage

KStepNewtonMove(
  param.cur,
  gradhess.fun.name,
  KStep,
  Params,
  hessMethod,
  Y,
  x0,
  callParam,
  splineArgs,
  priorArgs,
  Params_Transform
)

Arguments

param.cur	"matrix". The initial values for the Newton update.
gradhess.fun.name	NA
KStep	NA
Params	NA
hessMethod	NA
Y	NA
x0	NA
callParam	NA
splineArgs	NA
priorArgs	NA
Params_Transform	NA

Value

"list". See bellow. 'gradObs.cur': The gradient matrix. 'invHessObs.cur': The inverse hessian matrix. 'param.cur': The updated parameters after K step Newton iterations.

Author(s)

Feng Li, Department of Statistics, Stockholm University, Sweden.

feng-li/movingknots documentation built on March 30, 2021, 11:58 a.m.