Dispatches pool methods based upon results object class. See
pool() for details.
pool_internal(results, conf.level, alternative, type, D, ...)# S3 method for jackknife
pool_internal(results, conf.level, alternative, type, D, ...)
# S3 method for bootstrap
pool_internal(
results,
conf.level,
alternative,
type = c("percentile", "normal"),
D,
...
)
# S3 method for bmlmi
pool_internal(results, conf.level, alternative, type, D, ...)
# S3 method for rubin
pool_internal(results, conf.level, alternative, type, D, rubin_df_method, ...)
A list containing the pooled results for a single parameter with elements
est (point estimate), ci (confidence interval), se (standard error)
and pvalue (p-value). The specific computation is determined by the class
of results via S3 dispatch.
a list of results i.e. the x$results element of an
analyse object created by analyse()).
confidence level of the returned confidence interval. Must be a single number between 0 and 1. Default is 0.95.
a character string specifying the alternative hypothesis,
must be one of "two.sided" (default), "greater" or "less".
a character string of either "percentile" (default) or
"normal". Determines what method should be used to calculate the bootstrap confidence
intervals. See details.
Only used if method_condmean(type = "bootstrap") was specified
in the original call to draws().
numeric representing the number of imputations between each bootstrap sample in the BMLMI method.
not used.
a character string specifying the degrees-of-freedom
approximation used when pooling with Rubin's rules. "barnard-rubin" (default)
uses the Barnard-Rubin (1999) small-sample adjustment, while "rubin"
uses the approximation from Rubin (1987). Ignored for other pooling methods.