extract_random_effects: Extract random effects

In m-clark/mixedup: Miscellaneous functions for mixed models

Extract random effects

Description

Extracts the random effects and their standard errors.

Usage

extract_random_effects(
  model,
  re = NULL,
  ci_level = 0.95,
  digits = 3,
  add_group_N = FALSE,
  ...
)

## S3 method for class 'merMod'
extract_random_effects(
  model,
  re = NULL,
  ci_level = 0.95,
  digits = 3,
  add_group_N = FALSE,
  condvar = TRUE,
  ...
)

## S3 method for class 'glmmTMB'
extract_random_effects(
  model,
  re = NULL,
  ci_level = 0.95,
  digits = 3,
  add_group_N = FALSE,
  component = "cond",
  condvar = TRUE,
  ...
)

## S3 method for class 'lme'
extract_random_effects(
  model,
  re = NULL,
  ci_level = NULL,
  digits = 3,
  add_group_N = FALSE,
  ...
)

## S3 method for class 'brmsfit'
extract_random_effects(
  model,
  re = NULL,
  ci_level = 0.95,
  digits = 3,
  add_group_N = FALSE,
  component = NULL,
  ...
)

## S3 method for class 'stanreg'
extract_random_effects(
  model,
  re = NULL,
  ci_level = 0.95,
  digits = 3,
  add_group_N = FALSE,
  component = NULL,
  ...
)

## S3 method for class 'gam'
extract_random_effects(
  model,
  re = NULL,
  ci_level = 0.95,
  digits = 3,
  add_group_N = FALSE,
  ...
)

extract_ranef(
  model,
  re = NULL,
  ci_level = 0.95,
  digits = 3,
  add_group_N = FALSE,
  ...
)

Arguments

model	An appropriate model. See details.
re	The name of the grouping variable for the random effects. Default is NULL to return all.
ci_level	Where possible, confidence level < 1, typically above 0.90. A value of 0 will not report it. Default is .95. Not applicable to nlme objects.
digits	Rounding. Default is 3.
add_group_N	Add group sample sizes to output? Default is FALSE.
...	Other arguments specific to the method. Unused at present.
condvar	Include conditional variance. Used in lme4 and glmmTMB objects.
component	For glmmTMB objects, which of the two components 'cond' or 'zi' to select. Default is 'cond'. For brmsfit objects, this can filter results to a certain part of the output, e.g. 'sigma' or 'zi' of distributional models, or a specific outcome name of a multivariate model. In this case component is a regular expression that ends the name of the parameters of the output (e.g. '__component'). For stanreg objects, this could be the

Details

Relative to ranef for the various packages, this just adds the standard errors and cluster ids as columns, and uncertainty intervals.

Current models supported:

merMod

glmmTMB

brms

nlme

brms

rstanarm

mgcv

Value

data frame of the random effects

Note

The nlme package only provides the estimated random effect parameters, not their uncertainty, so it isn't provided.

merMod and glmmTMB objects results are based on the estimated conditional variances, i.e. condvar = TRUE. This is likely an underestimate relative to brms results.

For mgcv, the Vp (Bayesian) estimated variance covariance matrix is used.

See Also

lme4::ranef(), glmmTMB::ranef(), nlme::ranef(), brms::ranef(), rstanarm::ranef(), mgcv::gamObject(), mgcv::smooth.construct.re.smooth.spec()

Other extract: extract_cor_structure(), extract_fixed_effects(), extract_het_var(), extract_model_data(), extract_random_coefs(), extract_vc()

Examples

library(lme4)
library(mixedup)

lmer_model <- lmer(Reaction ~ Days + (1 + Days | Subject), data = sleepstudy)
extract_random_effects(lmer_model)

m-clark/mixedup documentation built on Oct. 15, 2022, 8:55 a.m.