check.analytical

object

An original data frame or list containing the model response variable and covariates.

data

A positive scalar (default is 1e-6) giving an increment for finite difference approximation.

This function calculates the finite-difference approximation of the GCV/UBRE gradient for the fitted 
         model and compares it with the analytical gradient.

models

regression

smooth

Routines for generalized additive modelling under shape
        constraints on the component functions of the linear predictor.
        Models can contain multiple shape constrained (univariate
        and/or bivariate) and unconstrained terms. The routines of
        mgcv(gam) package are used for setting up the model matrix,
        printing and plotting the results.  Penalized likelihood
        maximization based on Newton-Raphson method is used to fit a
        model with multiple smoothing parameter selection by GCV or
        UBRE/AIC.

check.analytical: Checking the analytical gradient of the GCV/UBRE score

Description

Usage

Arguments

Value

See Also