Get model parameters from Bayesian models — get

Returns the coefficients (or posterior samples for Bayesian models) from a model.

Usage

# S3 method for BGGM
get_parameters(
  x,
  component = c("correlation", "conditional", "intercept", "all"),
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for MCMCglmm
get_parameters(
  x,
  effects = c("fixed", "random", "all"),
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for BFBayesFactor
get_parameters(
  x,
  effects = c("all", "fixed", "random"),
  component = c("all", "extra"),
  iterations = 4000,
  progress = FALSE,
  verbose = TRUE,
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for stanmvreg
get_parameters(
  x,
  effects = c("fixed", "random", "all"),
  parameters = NULL,
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for brmsfit
get_parameters(
  x,
  effects = "fixed",
  component = "all",
  parameters = NULL,
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for stanreg
get_parameters(
  x,
  effects = c("fixed", "random", "all"),
  component = c("location", "all", "conditional", "smooth_terms", "sigma",
    "distributional", "auxiliary"),
  parameters = NULL,
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for bayesx
get_parameters(
  x,
  component = c("conditional", "smooth_terms", "all"),
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for bamlss
get_parameters(
  x,
  component = c("all", "conditional", "smooth_terms", "location", "distributional",
    "auxiliary"),
  parameters = NULL,
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for sim.merMod
get_parameters(
  x,
  effects = c("fixed", "random", "all"),
  parameters = NULL,
  summary = FALSE,
  centrality = "mean",
  ...
)

# S3 method for sim
get_parameters(x, parameters = NULL, summary = FALSE, centrality = "mean", ...)

Arguments

x: A fitted model.
component: Which type of parameters to return, such as parameters for the conditional model, the zero-inflated part of the model, the dispersion term, the instrumental variables or marginal effects be returned? Applies to models with zero-inflated and/or dispersion formula, or to models with instrumental variables (so called fixed-effects regressions), or models with marginal effects from mfx. May be abbreviated. Note that the conditional component is also called count or mean component, depending on the model. There are three convenient shortcuts: component = "all" returns all possible parameters. If component = "location", location parameters such as conditional, zero_inflated, smooth_terms, or instruments are returned (everything that are fixed or random effects - depending on the effects argument - but no auxiliary parameters). For component = "distributional" (or "auxiliary"), components like sigma, dispersion, beta or precision (and other auxiliary parameters) are returned.
summary: Logical, indicates whether the full posterior samples (summary = FALSE)) or the summarized centrality indices of the posterior samples (summary = TRUE)) should be returned as estimates.
centrality: Only for models with posterior samples, and when summary = TRUE. In this case, centrality = "mean" would calculate means of posterior samples for each parameter, while centrality = "median" would use the more robust median value as measure of central tendency.
...: Currently not used.
effects: Should parameters for fixed effects, random effects or both be returned? Only applies to mixed models. May be abbreviated.
iterations: Number of posterior draws.
progress: Display progress.
verbose: Toggle messages and warnings.
parameters: Regular expression pattern that describes the parameters that should be returned.

Value

The posterior samples from the requested parameters as data frame. If summary = TRUE, returns a data frame with two columns: the parameter names and the related point estimates (based on centrality).

Details

In most cases when models either return different "effects" (fixed, random) or "components" (conditional, zero-inflated, ...), the arguments effects and component can be used.

BFBayesFactor Models

Note that for BFBayesFactor models (from the BayesFactor package), posteriors are only extracted from the first numerator model (i.e., model[1]). If you want to apply some function foo() to another model stored in the BFBayesFactor object, index it directly, e.g. foo(model[2]), foo(1/model[5]), etc. See also bayestestR::weighted_posteriors().

Examples

data(mtcars)
m <- lm(mpg ~ wt + cyl + vs, data = mtcars)
get_parameters(m)
#>     Parameter   Estimate
#> 1 (Intercept) 38.7460642
#> 2          wt -3.2463673
#> 3         cyl -1.3641033
#> 4          vs  0.5241721