LMMstar (version 1.1.0)

effects.lmm: Effects Derived For Linear Mixed Model

Description

Estimate average counterfactual outcome or contrast of outcome from linear mixed models.

Usage

# S3 method for lmm
effects(
  object,
  variable,
  newdata = NULL,
  type = c("identity", "none"),
  conditional = NULL,
  rhs = NULL,
  repetition = NULL,
  multivariate = FALSE,
  prefix.time = NULL,
  prefix.var = TRUE,
  sep.var = ",",
  ...
)

Arguments

object

a lmm object.

variable

[character] the variable relative to which the effect should be computed.

newdata

[data.frame] a dataset reflecting the covariate distribution relative to which the average outcome or contrast should be computed.

type

[character] should the average counterfactual outcome for each variable level be evaluated ("identity")? Or the difference in average counterfactual outcome between each pair of variable level ("difference")? Can have an second element to consider a transformation of the outcome: the change from baseline ("change"), area under the outcome curve ("auc"), or area under the outcome curve minus baseline ("auc-b").

conditional

[character] variable conditional to which the average conterfactual outcome or treatment effect should be computed.

rhs

[numeric] the right hand side of the hypothesis.

repetition

[character vector] repetition at which the effect should be assessed. By default it will be assessed at all repetitions.

multivariate

[logical] should a multivariate Wald test be used to simultaneously test all null hypotheses.

prefix.time

[character] When naming the estimates, text to be pasted before the value of the repetition variable. Only relevant when type = "aoc" or type = "ate".

prefix.var

[logical] When naming the estimates, should the variable name be added or only the value?

sep.var

[character] When naming the estimates, text to be pasted between the values to condition on. Only relevant when type = "aoc" or type = "ate".

...

Arguments passed to anova.lmm.

Examples

#### simulate data in the long format ####
set.seed(10)
dL <- sampleRem(100, n.times = 3, format = "long")

#### Linear Mixed Model ####
eUN.lmm <- lmm(Y ~ visit + X1 + X2 + X5,
               repetition = ~visit|id, structure = "UN", data = dL)

## outcome
effects(eUN.lmm, variable = "X1")
effects(eUN.lmm, type = "difference", variable = "X1")
effects(eUN.lmm, type = "difference", variable = "X1", repetition = "3")

## change
effects(eUN.lmm, type = "change", variable = "X1")
effects(eUN.lmm, type = "change", variable = "X1", conditional = NULL)
effects(eUN.lmm, type = c("change","difference"), variable = "X1")

## auc
effects(eUN.lmm, type = "auc", variable = "X1")
effects(eUN.lmm, type = c("auc","difference"), variable = "X1")

#### fit Linear Mixed Model with interaction ####
dL$X1.factor <- as.factor(dL$X1)
dL$X2.factor <- as.factor(dL$X2)
eUN.lmmI <- lmm(Y ~ visit * X1.factor + X2.factor + X5,
               repetition = ~visit|id, structure = "UN", data = dL)

## average counterfactual conditional to a categorical covariate
effects(eUN.lmmI, variable = "X1.factor",
        conditional = c("X2.factor"), repetition = "3")
effects(eUN.lmmI, type = "change", variable = "X1.factor",
        conditional = c("X2.factor"), repetition = "3")
effects(eUN.lmmI, type = "auc", variable = "X1.factor",
        conditional = c("X2.factor"), repetition = "3")

## average difference in counterfactual conditional to a categorical covariate
effects(eUN.lmmI, type = "difference", variable = "X1.factor",
        conditional = c("X2.factor"), repetition = "3")
effects(eUN.lmmI, type = c("change","difference"), variable = "X1.factor",
        conditional = c("X2.factor"), repetition = "3")
effects(eUN.lmmI, type = c("auc","difference"), variable = "X1.factor",
        conditional = c("X2.factor"), repetition = "3")

## average difference in counterfactual conditional to a covariate
effects(eUN.lmmI, type = "difference", variable = "X1.factor",
        conditional = list(X5=0:2), repetition = "3")
effects(eUN.lmmI, type = c("difference","change"), variable = "X1.factor",
        conditional = list(X5=0:2))