[R-meta] Random-effects meta-analyses with inverse-variance weights cannot include studies with sample sizes of two?
What kind of effect size measure would you compute based on this? And what would be the corresponding sampling variance? Best, Wolfgang -----Original Message----- From: Patrizio Tressoldi [mailto:patrizio.tressoldi at unipd.it] Sent: Thursday, 08 November, 2018 19:01 To: Viechtbauer, Wolfgang (SP); Michael Dewey; r-sig-meta-analysis at r-project.org Subject: Re: [R-meta] Random-effects meta-analyses with inverse-variance weights cannot include studies with sample sizes of two? Il 08/11/2018 16:31, Viechtbauer, Wolfgang (SP) ha scritto:
I wonder what effect size / oucome measure can sensibly be computed based on two subjects. For example, for measures based on two groups (e.g., raw or standardized mean difference, risk difference, log risk/odds ratios), this would imply that there is a single subject in each group.
Precisely. In this specific case, two single participants contributed to a percentage of hits, e.g. .30 and .40 I expect that the sample estimation is quite poor, but I don't see any impediment on obtaining an effect size, or not? Best Patrizio -- Patrizio E. Tressoldi Ph.D. Dipartimento di Psicologia Generale Universit? di Padova via Venezia 8 35131 Padova - ITALY http://www.patriziotressoldi.it https://orcid.org/0000-0002-6404-0058 Science of Consciousness Research Group http://dpg.unipd.it/en/soc Make war history support http://www.emergency.it