View source: R/bivar.smooth.const.R
smooth.construct.tesmi1.smooth.spec | R Documentation |
This is a special method function
for creating tensor product bivariate smooths monotone increasing in the first covariate which is built by
the mgcv
constructor function for smooth terms, smooth.construct
.
It is constructed from a pair of single penalty
marginal smooths. This tensor product is specified by model terms such as s(x1,x2,k=c(q1,q2),bs="tesmi1",m=2)
.
The basis for the second marginal smooth can be specified as a two letter character string of the argument xt
(eg xt="cc"
to specify cyclic cubic regression spline). See example below. The default basis for the second marginal smooth is P-spline. Cyclic cubic regression spline ("cc"
) is implemented in addition to the P-spline. See an example below on how to call for it.
## S3 method for class 'tesmi1.smooth.spec'
smooth.construct(object, data, knots)
object |
A smooth specification object, generated by an |
data |
A data frame or list containing the values of the elements of |
knots |
An optional list containing the knots corresponding to |
An object of class "tesmi1.smooth"
. In addition to the usual
elements of a smooth class documented under smooth.construct
of the mgcv
library,
this object contains:
p.ident |
A vector of 0's and 1's for model parameter identification: 1's indicate parameters which will be exponentiated, 0's - otherwise. |
Zc |
A matrix of identifiability constraints. |
margin.bs |
A two letter character string indicating the (penalized) smoothing basis to use for the second unconstrained marginal smooth. (eg |
Natalya Pya <nat.pya@gmail.com>
Pya, N. and Wood, S.N. (2015) Shape constrained additive models. Statistics and Computing, 25(3), 543-559
Pya, N. (2010) Additive models with shape constraints. PhD thesis. University of Bath. Department of Mathematical Sciences
smooth.construct.tesmi2.smooth.spec
## Not run:
## tensor product `tesmi1' example...
## simulating data...
require(scam)
simu <- function(x,z) exp(4*x)/(1+exp(4*x))+2*sin(pi*z)
xs <- seq(-1,3,length=30); zs <- seq(0,1,length=30)
pr <- data.frame(x=rep(xs,30),z=rep(zs,rep(30,30)))
truth <- matrix(simu(pr$x,pr$z),30,30)
set.seed(24)
n <- 500
x <- runif(n)*4-1
z <- runif(n)
f <- simu(x,z)
y <- f + rnorm(n)*.3
## fit model ...
b <- scam(y~s(x,z,bs="tesmi1",k=c(10,10)))
old.par <- par(mfrow=c(2,2))
persp(xs,zs,truth);title("truth")
vis.scam(b,theta=40,phi=20);title("tesmi1")
plot(b,se=TRUE)
plot(y,b$fitted.values,xlab="Simulated data",ylab="Fitted data")
par(old.par)
## example with cyclic cubic regression spline along the second covariate...
simu2 <- function(x,z)
exp(4*x)/(1+exp(4*x))+sin(2*pi*z)
xs <- seq(-1,3,length=30); zs <- seq(0,1,length=30)
pr <- data.frame(x=rep(xs,30),z=rep(zs,rep(30,30)))
truth2 <- matrix(simu2(pr$x,pr$z),30,30)
set.seed(2)
n <- 500
x <- runif(n)*4-1
z <- runif(n)
f <- simu2(x,z)
y <- f + rnorm(n)*.2
## fit model ...
b1 <- scam(y~s(x,z,bs="tesmi1",xt=list("cc"),k=10))
old.par <- par(mfrow=c(2,2))
plot(b1,se=TRUE)
vis.scam(b1,theta=40,phi=20);title("tesmi1, cyclic")
plot(y,b1$fitted.values,xlab="Simulated data",ylab="Fitted data")
persp(xs,zs,truth2,theta = 30, phi = 40);title("truth")
par(old.par)
## End(Not run)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.