pooled_effect computes the pooled effect size
for a fitted RoBMA.reg and BiBMA.reg object.
pooled_effect(
object,
conditional = FALSE,
output_scale = NULL,
probs = c(0.025, 0.975),
...
)pooled_effect returns a list of tables of class 'BayesTools_table'.
a fitted RoBMA object
show the conditional estimates (assuming that the
alternative is true). Defaults to FALSE. Only available for
type == "ensemble".
transform the meta-analytic estimates to a different
scale. Defaults to NULL which returns the same scale as the model was estimated on.
quantiles of the posterior samples to be displayed.
Defaults to c(.025, .975)
additional arguments
The meta-regression specification results in the intercept corresponding to the adjusted effect estimate (i.e., adjusting for the effect of moderators). In case of moderators inbalance, the adjusted effect estimate might not be representative of the sample of studies. The pooled effect size function averages the effect size estimate across the moderators proportionately to the moderators levels observed in the data set. Note that there is no Bayes factor test for the presence of the pooled effect (the summary function provides the adjusted effect and the test for the presence of the adjusted effect).
The conditional estimate is calculated conditional on the presence of the adjusted effect (i.e., the intercept).
adjusted_effect()