summary.causal_model: Summarizing causal models

In CausalQueries: Make, Update, and Query Binary Causal Models

Summarizing causal models

Description

summary method for class "causal_model".

Usage

## S3 method for class 'causal_model'
summary(object, include = NULL, ...)

## S3 method for class 'summary.causal_model'
print(x, what = NULL, ...)

Arguments

object	An object of causal_model class produced using make_model or update_model.
include	A character string specifying the additional objects to include in summary. Defaults to NULL. See details for full list of available values.
...	Further arguments passed to or from other methods.
x	An object of summary.causal_model class, produced using summary.causal_model.
what	A character string specifying the objects summaries to print. Defaults to NULL printing causal statement, specification of nodal types and summary of model restrictions. See details for full list of available values.

Details

In addition to the default objects included in 'summary.causal_model' users can request additional objects via 'include' argument. Note that these additional objects can be large for complex models and can increase computing time. The 'include' argument can be a vector of any of the following additional objects:

• "parameter_matrix" A matrix mapping from parameters into causal types,

• "parameter_mapping" a matrix mapping from parameters into data types,

• "causal_types" A data frame listing causal types and the nodal types that produce them,

• "prior_distribution" A data frame of the parameter prior distribution,

• "ambiguities_matrix" A matrix mapping from causal types into data types,

• "type_prior" A matrix of type probabilities using priors.

print.summary.causal_model reports causal statement, full specification of nodal types and summary of model restrictions. By specifying 'what' argument users can instead print a custom summary of any set of the following objects contained in the 'summary.causal_model':

• "statement" A character string giving the causal statement,

• "nodes" A list containing the nodes in the model,

• "parents" A list of parents of all nodes in a model,

• "parents_df" A data frame listing nodes, whether they are root nodes or not, and the number and names of parents they have,

• "parameters" A vector of 'true' parameters,

• "parameters_df" A data frame containing parameter information,

• "parameter_names" A vector of names of parameters,

• "parameter_mapping" A matrix mapping from parameters into data types,

• "parameter_matrix" A matrix mapping from parameters into causal types,

• "causal_types" A data frame listing causal types and the nodal types that produce them,

• "nodal_types" A list with the nodal types of the model,

• "data_types" A list with the all data types consistent with the model; for options see '"?get_all_data_types"',

• "prior_hyperparameters" A vector of alpha values used to parameterize Dirichlet prior distributions; optionally provide node names to reduce output ‘inspect(prior_hyperparameters, c(’M', 'Y'))'

• "prior_distribution" A data frame of the parameter prior distribution,

• "prior_event_probabilities" A vector of data (event) probabilities given a single (sepcified) parameter vector; for options see '"?get_event_probabilities"',

• "ambiguities_matrix" A matrix mapping from causal types into data types,

• "type_prior" A matrix of type probabilities using priors,

• "type_posterior" A matrix of type probabilities using posteriors,

• "posterior_distribution" A data frame of the parameter posterior distribution,

• "posterior_event_probabilities" A sample of data (event) probabilities from the posterior,

• "data" A data frame with data that was used to update model,

• "stanfit" A 'stanfit' object generated by Stan,

• "stan_summary" A 'stanfit' summary with updated parameter names.

Value

Returns the object of class summary.causal_model that preserves the list structure of causal_model class and adds the following additional objects:

• "parents" a list of parents of all nodes in a model,

• "parameters" a vector of 'true' parameters,

• "parameter_names" a vector of names of parameters,

• "data_types" a list with the all data types consistent with the model; for options see "?get_all_data_types",

• "prior_event_probabilities" a vector of prior data (event) probabilities given a parameter vector; for options see "?get_event_probabilities",

• "prior_hyperparameters" a vector of alpha values used to parameterize Dirichlet prior distributions; optionally provide node names to reduce output "inspect(prior_hyperparameters, c('M', 'Y'))"

Examples

model <-
  make_model("X -> Y")

model |>
  update_model(
    keep_event_probabilities = TRUE,
    keep_fit = TRUE,
    data = make_data(model, n = 100)
  ) |>
  summary()



model <-
  make_model("X -> Y")

model <-
  model |>
  update_model(
    keep_event_probabilities = TRUE,
    keep_fit = TRUE,
    data = make_data(model, n = 100)
  )

print(summary(model), what = "type_posterior")
print(summary(model), what = "posterior_distribution")
print(summary(model), what = "posterior_event_probabilities")
print(summary(model), what = "data_types")
print(summary(model), what = "prior_hyperparameters")
print(summary(model), what = c("statement", "nodes"))
print(summary(model), what = "parameters_df")
print(summary(model), what = "posterior_event_probabilities")
print(summary(model), what = "posterior_distribution")
print(summary(model), what = "data")
print(summary(model), what = "stanfit")
print(summary(model), what = "type_posterior")

# Large objects have to be added to the summary before printing
print(summary(model, include = "ambiguities_matrix"),
  what = "ambiguities_matrix")

CausalQueries documentation built on April 3, 2025, 7:46 p.m.