sop.control: Function for controlling SOP fitting

In SOP: Generalised Additive P-Spline Regression Models Estimation

Function for controlling SOP fitting

Description

The function controls some of the fitting parameters of sop. Typically only used when calling sop().

Usage

sop.control(maxit = 200, epsilon = 1e-6, trace = FALSE)

Arguments

maxit	numerical value indicating the maximum number of iterations. Default set to 200 (see Details).
epsilon	numerical value indicating the tolerance for the convergence criterion. Default set to 1e-6 (see Details).
trace	logical indicating if output should be produced for each iteration.

Details

For Gaussian response variables, the implemented algorithm is an iterative procedure, with the fixed and random effects as well as the variance components being updated at each iteration. To check the convergence of this iterative procedure, the (REML) deviance is monitored. For non-Gaussian response variables, estimation is based on Penalized Quasi-likelihood (PQL) methods. Here, the algorithm is a two-loop algorithm: the outer loop corresponds to the Fisher-Scoring algorithm (monitored on the basis of the change in the linear predictor between consecutive iterations), and the inner loop corresponds to that described for the Gaussian case.

Value

A list with the arguments as components.

References

Rodriguez-Alvarez, M.X., Lee, D. J., Kneib, T., Durban, M., and Eilers, P. (2015). Fast smoothing parameter separation in multidimensional generalized P-splines: the SAP algorithm. Statistics and Computing, 25 (5), 941–957.

Rodriguez-Alvarez, M.X., Durban, M., Lee, D. J. and Eilers, P. (2019). On the estimation of variance parameters in non-standard generalised linear mixed models: application to penalised smoothing. Statistics and Computing, 29 (3), 483–500.

See Also

sop.

Examples

library(SOP)
# Simulate the data
set.seed(123)
n <- 1000
sigma <- 0.5
x <- runif(n)
f0 <- function(x) 2*sin(pi*x)
f <- f0(x)
y <- f + rnorm(n, 0, sigma)
dat <- data.frame(x = x, y = y)

# Fit the model
m0 <- sop(formula = y ~ f(x, nseg = 10), data = dat, control = list(trace = FALSE))
summary(m0)

SOP documentation built on Sept. 16, 2023, 1:07 a.m.