A two-sided linear formula object describing the model, with the
response (effect sizes) on the left of a ~ operator and the moderator
variables, separated by +, :, * operators, on the right. NOTE:
MetaWin was limited to analyses with a single moderat
weights
A vector of effect size variances that will be used as
weights for the meta-analysis.
effects_model
The default is "random", which specifies a
random-effects meta-analysis. Other options include "fixed"
which presents fixed-effect analyses.
data
An optional data frame containing the variables named in model
and weights.
bootstraps
The number of bootstraps used to estimate confidence
intervals. As with 'MetaWin' 2.0, the default is 999.
References
Rosenberg, M.S., Adams, D.C., and Gurevitch, J. 2000.
MetaWin: Statistical Software for Meta-Analysis. Sinauer Associates
Sunderland, Massachusetts.