Package index • metaselection

Model-Fitting

Functions to fit and evaluate selection models with robust variance estimation or cluster bootstrapping

selection_model(): Estimate step or beta selection model
selection_plot(): Plot the selection weights implied by an estimated selection model.
selection_wts(): Calculate model-implied weights for specified p-values.
print(<selmodel>): Print results from a selmodel object
summary(<selmodel>): Summarize results from a selmodel object
define_priors(): Define prior penalty functions for selection model parameters
p_area(): Calculate area under the selection weight function from a selmodel object

Example datasets from published meta-analyses and one dataset containing a distribution of primary study characteristics

self_control: Self-Control Training Meta-Analysis
interleaved_learning: Interleaved Learning Meta-Analysis
practice_facilitation: Practice Facilitation Meta-Analysis
wwc_es: What Works Clearinghouse sample size and effect size distribution data

Functions to simulate meta-analytic data, including data subject to selective outcome reporting

r_meta(): Generate meta-analytic data
step_fun(): Censor meta-analytic dataset based on a step-function model
beta_fun(): Censor meta-analytic dataset based on the beta-density model
n_ES_empirical(): Simulate empirical distribution of sample size and number of effect sizes
n_ES_param(): Simulate empirical distribution of sample size and number of effect sizes