mcmcsae (version 0.8.1)

s: Specify a smooth term component of the linear predictor

Description

This function can be used inside the formula specification of the linear predictor in create_sampler or generate_data. The smooth term is set up by the smooth term specification function s of package mgcv. The smooth term is usually composed of random (penalised) effects as well as a few fixed (unpenalised) effects, not including an intercept.

Usage

s(..., unit.precision = FALSE, name = "", debug = FALSE)

Value

An object with precomputed quantities and functions for sampling from prior or conditional posterior distributions for this model component, intended for internal use by other package functions.

Arguments

...

parameters passed to mgcv::s. Note that variables appearing in ... must be present in the data frame passed to the data argument of create_sampler or generate_data.

unit.precision

to be implemented.

name

the name of the model component. By default the name will be 's' with the number of the model term attached. This name is used in the output of the MCMC simulation function MCMCsim. The name is appended by '_f' for any unpenalised (fixed) effects, if any, and by '_r' for the penalised (random) effects.

debug

if TRUE a breakpoint is set at the beginning of the posterior draw function associated with this model component. Mainly intended for developers.

References

S.N. Wood (2017). Generalized additive models: an introduction with R. Chapman and Hall/CRC.

Examples

if (FALSE) {
library(mgcv)
set.seed(0)
dat <- gamSim(5, n=200, scale=2)
b <- gam(y ~ x0 + s(x1) + s(x2) + s(x3), data=dat)

sampler <- create_sampler(
  y ~ x0 + s(x1) + s(x2) + s(x3), data=dat
)
sim <- MCMCsim(sampler, store.all=TRUE)
(summ <- summary(sim))
plot(
  coef(b),
  c(summ$reg1[, "Mean"],
    summ$s2_r[, "Mean"], summ$s2_f[, "Mean"],
    summ$s3_r[, "Mean"], summ$s3_f[, "Mean"],
    summ$s4_r[, "Mean"], summ$s4_f[, "Mean"]
   )
); abline(0, 1)
predb <- predict(b, newdata=dat[1:5, ])
pred <- predict(sim, newdata=dat[1:5, ], type="response")
(summpred <- summary(pred))
plot(predb, summpred[, "Mean"]); abline(0, 1)
}