[R-meta] Open AI ChatGPT

[Viechtbauer, Wolfgang (NP)]

Dear Patrizio,

That code is nonsense. One cannot pass multiple columns to the yi argument. There even is a check in rma.mv() to make sure people don't try to do this:

Error in rma.mv(...):                  
  The object/variable specified for the 'yi' argument is a data frame with multiple columns.

Also, V should either be a vector or a kxk matrix where k is the length of yi. 

This is now the second example where ChatGPT is providing either misleading or entirely incorrect info about how to use metafor:

https://scholar.social/@wviechtb/109516606479461002

Best,
Wolfgang

>-----Original Message-----
>From: R-sig-meta-analysis [mailto:r-sig-meta-analysis-bounces using r-project.org] On
>Behalf Of Patrizio E Tressoldi
>Sent: Wednesday, 28 December, 2022 15:24
>To: r-sig-meta-analysis using r-project.org
>Subject: [R-meta] Open AI ChatGPT
>
>I asked the following question: "/I need the metafor syntax for a mixed
>model with two dependent variable and three categorical moderators/"
>and I received the following syntax with detailed explanations:
>
>fit <- rma.mv(yi = dat[, c("yi1", "yi2")],
>               V = dat[, c("vi1", "vi2")],
>               mods = ~ moderator1 + moderator2 + moderator3,
>               random = ~ 1 | grouping_variable,
>               data = dat)
>
>I'm curious what Wolfgang and James think about.
>
>Patrizio
>
>--
>Patrizio E. Tressoldi Ph.D.
>Science of Consciousness Research Group
>Studium Patavinum
>Università di Padova
>Padova - ITALY
>http://www.patriziotressoldi.it
>https://socrg.org
>https://orcid.org/0000-0002-6404-0058
>https://opensciences.org/about/manifesto-for-a-post-materialist-science
>
>Make war history
>supporthttps://en.emergency.it