PublicationBiasBenchmark (version 0.1.3)

run_method: Generic method function for publication bias correction

Description

This function provides a unified interface to various publication bias correction methods. The specific method is determined by the first argument. See vignette("Adding_New_Methods", package = "PublicationBiasBenchmark") for details of extending the package with new methods

Usage

run_method(method_name, data, settings = NULL, silent = FALSE)

Value

A data frame with standardized method results

Arguments

method_name

Character string specifying the method type

data

Data frame containing yi (effect sizes) and sei (standard errors)

settings

Either a character identifying a method version or list containing method-specific settings. An emty input will result in running the default (first implemented) version of the method.

silent

Logical indicating whether error messages from the method should be suppressed.

Output Structure

The returned data frame follows a standardized schema that downstream functions rely on. All methods return the following columns:

• method (character): The name of the method used.

• estimate (numeric): The meta-analytic effect size estimate.

• standard_error (numeric): Standard error of the estimate.

• ci_lower (numeric): Lower bound of the 95% confidence interval.

• ci_upper (numeric): Upper bound of the 95% confidence interval.

• p_value (numeric): P-value for the estimate.

• BF (numeric): Bayes Factor for the estimate.

• convergence (logical): Whether the method converged successfully.

• note (character): Additional notes describing convergence issues.

Some methods may include additional method-specific columns beyond these standard columns. Use get_method_extra_columns() to query which additional columns a particular method returns.

Examples

# Example usage with RMA method
data <- data.frame(
  yi = c(0.2, 0.3, 0.1, 0.4),
  sei = c(0.1, 0.15, 0.08, 0.12)
)
result <- run_method("RMA", data, "default")