coef.mlmm: Extract Coefficients From Multiple Linear Mixed Models

In bozenne/repeated: Repeated Measurement Models for Discrete Times

Extract Coefficients From Multiple Linear Mixed Models

Description

Combine estimated parameters or linear contrasts applied on parameters from group-specific linear mixed models.

Usage

## S3 method for class 'mlmm'
coef(
  object,
  effects = "Wald",
  method = "none",
  p = NULL,
  ordering = "model",
  backtransform = object$args$backtransform,
  transform.sigma = "none",
  transform.k = "none",
  transform.rho = "none",
  transform.names = TRUE,
  simplify = TRUE,
  ...
)

Arguments

object	a mlmm object.
effects	[character] By default will output the estimates relative to the hypotheses being tested ("Wald"). But can also output all model coefficients ("all"), or only coefficients relative to the mean ("mean" or "fixed"), or only coefficients relative to the variance structure ("variance"), or only coefficients relative to the correlation structure ("correlation").
method	[character vector] should the estimated value for the linear contrasts be output (one of "none", "bonferroni", ..., "single-step2") and/or pooled linear contrast estimate(s) ("average", "pool.se", "pool.gls", "pool.gls1", "pool.rubin", "p.rejection")? Only relevant when effects = "Wald".
p	[list of numeric vector] values for the model parameters to be used to evaluate the estimates relative to the hypotheses being tested. Only relevant if differs from the fitted values.
ordering	[character] should the output be ordered by name of the linear contrast ("contrast") or by model ("model").
backtransform	[logical] should the estimate be back-transformed? Only relevant when effects="Wald".
transform.sigma	[character] Transformation used on the variance coefficient for the reference level. One of "none", "log", "square", "logsquare". Ignored when effects="Wald".
transform.k	[character] Transformation used on the variance coefficients relative to the other levels. One of "none", "log", "square", "logsquare", "sd", "logsd", "var", "logvar". Ignored when effects="Wald".
transform.rho	[character] Transformation used on the correlation coefficients. One of "none", "atanh", "cov". Ignored when effects="Wald".
transform.names	[logical] Should the name of the coefficients be updated to reflect the transformation that has been used? Ignored when effects="Wald".
simplify	[logical] should the output be a vector or a list with one element specific to each possible ordering (i.e. contrast or model). Only relevant when argument method refers to multiple comparisons and not to a pooling method.
...	Not used. For compatibility with the generic method.

bozenne/repeated documentation built on July 16, 2025, 11:16 p.m.