scam (version 1.2-21)

scam.emmeans.support: Support Functions for emmeans

Description

Function required for compatibility of scam with the emmeans package. The function is not normally called directly, but rather service routines for emmeans function of the emmeans package.

Usage

recover_data.scam(object, ...)

Arguments

object

A fitted model object of the class scam as produced by scam().

...

Additional parameters that may be supported by the method.

References

Searle, S. R., Speed, F. M., and Milliken, G. A. (1980). Population Marginal Means in the Linear Model: An Alternative to Least Squares Means. The American Statistician, 34(4), 216-221. https://doi.org/10.1080/00031305.1980.10483031

Examples

# \donttest{
require(scam)
require(emmeans)
set.seed(2)
n <- 100
x <- sort(runif(n,-.5,.5))
f <- -20*x^2
fac <- as.factor(sample(1:3,n,replace=TRUE))
y <- ifelse(fac == 1, 4, ifelse(fac == 2, 1, -2)) + 
      f + rnorm(n, 0, 1.5)
dat <- data.frame(y=y,x=x,fac=fac)
m <- scam(y ~ fac+s(x,bs="cv"), data=dat)
em <- emmeans(m, ~ fac)
em
pairs(em)
 # }