Publication Bias Adjustment — publication

Fits publication-bias models from a fitted mars object. Implements the beta selection model by Citkowicz and Vevea (2017) and a beta-binomial selection model over p-value bins, plus a logistic selection model.

publication_bias(
  mars_object,
  method = c("beta_selection", "beta_binomial", "logistic_selection"),
  p_value_tail = c("two.sided", "right", "left"),
  n_bins = 10,
  maxit = 2000,
  integration_points = 121,
  integration_limit = 8,
  funnel_plot = FALSE,
  funnel_args = list(),
  control = list(),
  ...
)

Arguments

mars_object: A fitted object returned by mars.
method: Publication-bias method. One of "beta_selection", "beta_binomial", or "logistic_selection".
p_value_tail: P-value tail used for selection weights.
n_bins: Number of p-value bins for "beta_binomial".
maxit: Maximum optimization iterations.
integration_points: Number of points used for numerical integration.
integration_limit: Absolute z-limit used in numerical integration.
funnel_plot: Logical; if TRUE, draws a funnel plot from the fitted publication-bias model.
funnel_args: Optional named list passed to funnel_plot when funnel_plot = TRUE.
control: Optional named list passed to optim.
...: Unused. Optimization controls should be supplied through control; optimization uses "BFGS" internally.

Value

A list of class pub_bias with adjusted coefficients, selection parameters, selection weights, an Egger-type small-study-effects check, an adjusted/reference center for funnel plotting, model data for plotting, an adjusted-vs-unadjusted effect summary table, optimization diagnostics, and a standard-error diagnostic note when Hessian-based SEs are unstable. The selection_weights component is a p-value grid with weights for beta_selection and logistic_selection, and a bin-level weight table for beta_binomial.

References

Citkowicz, M., \& Vevea, J. L. (2017). A parsimonious weight function for modeling publication bias. Psychological Methods, 22(1), 28-41.