[R-meta] clubSandwich for rma.uni() models

Luke Martinez m@rt|nez|ukerm @end|ng |rom gm@||@com
Mon Nov 29 07:09:21 CET 2021

Dear Meta Experts,

(A) My understanding has been that the sandwich estimators are only
relevant to rma.mv() models where the structure of `V=` and/or
`random=` is suspected to be misspecified (hence SE of fixed effects
may be inaccurate).

(B) My understanding has also been that the sandwich estimators use
the highest clustering variable in purely nested models to compute the
dfs needed for fixed effects' p-value calculations.

rma.uni() models may loosely meet the (B) requirement. But it is not
obvious to me how such models may meet the (A) requirement.

Thus, how is clubSandwich:::vcovCR.rma.uni() relevant to rma.uni() models?


More information about the R-sig-meta-analysis mailing list