'Re: [R-sig-ME] Distributional Assumption in lmer()'

[prev in list] [next in list] [prev in thread] [next in thread] 

List:       r-sig-mixed-models
Subject:    Re: [R-sig-ME] Distributional Assumption in lmer()
From:       Ben Bolker <bbolker () gmail ! com>
Date:       2024-02-10 18:07:10
Message-ID: d3b80d0d-f55d-4f95-9cf1-7ca233085566 () gmail ! com
[Download RAW message or body]

   Yes.

  The mixed models task view 
<https://cran.r-project.org/web/views/MixedModels.html> says:

Robust/heavy-tailed estimation (downweighting the importance of extreme 
observations): robustlmm, robustBLME (Bayesian robust LME), CRTgeeDR for 
the doubly robust inverse probability weighted augmented GEE estimator. 
Some packages (brms, bamlss, mgcv with family = "scat", nlmixr2) allow 
heavy-tailed response distributions such as Student-t.

   (I just added glmmTMB and GLMMadaptive to this list of packages)

On 2024-02-10 9:45 a.m., Dimitris Rizopoulos wrote:
> It’s also available in GLMMadaptive: 
> https://drizopoulos.github.io/GLMMadaptive/articles/Custom_Models.html 
> <https://drizopoulos.github.io/GLMMadaptive/articles/Custom_Models.html>
> 
> ------------------------------------------------------------------------
> *Από:* Ο χρήστης R-sig-mixed-models 
> <r-sig-mixed-models-bounces@r-project.org> εκ μέρους του χρήστη Ben 
> Bolker <bbolker@gmail.com>
> *Στάλθηκε:* Παρασκευή, Φεβρουαρίου 9, 2024 23:11
> *Προς:* r-sig-mixed-models@r-project.org <r-sig-mixed-models@r-project.org>
> *Θέμα:* Re: [R-sig-ME] Distributional Assumption in lmer()
> 
> 
> Waarschuwing: Deze e-mail is afkomstig van buiten de organisatie. Klik 
> niet op links en open geen bijlagen, tenzij u de afzender herkent en 
> weet dat de inhoud veilig is.
> Caution: This email originated from outside of the organization. Do not 
> click links or open attachments unless you recognize the sender and know 
> the content is safe.
> 
> 
> 
> For what it's worth I think you can probably also do this in brms, if
> you want to go down the Bayesian rabbit hole ...
> 
> On 2024-02-09 5:01 p.m., Hedyeh Ahmadi wrote:
> > Thank you for the quick and informative reply.
> > 
> > Best,
> > 
> > Hedyeh Ahmadi, Ph.D.
> > Statistician
> > Keck School of Medicine
> > Department of Preventive Medicine
> > University of Southern California
> > 
> > LinkedIn
> > https://eur01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.linkedin.com% \
> > 2Fin%2Fhedyeh-ahmadi&data=05%7C02%7Cd.rizopoulos%40erasmusmc.nl%7Caebf617ef97a430f \
> > d59808dc29bc1797%7C526638ba6af34b0fa532a1a511f4ac80%7C0%7C0%7C638431135044801031%7 \
> > CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI \
> > 6Mn0%3D%7C0%7C%7C%7C&sdata=BflyM0EjMbj50sgQGJ%2FhucVgmaEwHNvTKeBcjExX6rc%3D&reserv \
> > ed=0<https://eur01.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.linkedin \
> > .com%2Fin%2Fhedyeh-ahmadi&data=05%7C02%7Cd.rizopoulos%40erasmusmc.nl%7Caebf617ef97 \
> > a430fd59808dc29bc1797%7C526638ba6af34b0fa532a1a511f4ac80%7C0%7C0%7C638431135044810 \
> > 000%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLC \
> > JXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=UWfXvLGMF6N20VDCaxX1TobXCRjBr6RiPTtDyQmyAwk%3D&reserved=0> \
> > <http://www.linkedin.com/in/hedyeh-ahmadi> 
> > 
> > 
> > 
> > ________________________________
> > From: R-sig-mixed-models <r-sig-mixed-models-bounces@r-project.org> on behalf of \
> >                 Ben Bolker <bolkerb@mcmaster.ca>
> > Sent: Friday, February 9, 2024 1:34 PM
> > To: r-sig-mixed-models@r-project.org <r-sig-mixed-models@r-project.org>
> > Subject: Re: [R-sig-ME] Distributional Assumption in lmer()
> > 
> > No, but:
> > 
> > (1) glmmTMB has this (family = t_family)
> > (2) you can achieve a similar goal with the robustlmm package
> > 
> > cheers
> > Ben Bolker
> > 
> > 
> > On 2024-02-09 3:42 p.m., Hedyeh Ahmadi wrote:
> > > Hello All,
> > > I was wondering if there is a way to implement t-distribution assumption \
> > > instead of family ="Gaussian" assumption in the lmer() function. 
> > > I am asking since I have been seeing heavy tails in my outcomes and it shows up \
> > > in my residual diagnostic QQplot hence I think a t-distribution would be more \
> > > appropriate compared to Normal distribution. 
> > > Any help would be greatly appreciated.
> > > 
> > > Best,
> > > 
> > > Hedyeh Ahmadi, Ph.D.
> > > Statistician
> > > Keck School of Medicine
> > > Department of Preventive Medicine
> > > University of Southern California
> > > 
> > > LinkedIn
> > > https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com \
> > > %2Fv3%2F__http%3A%2F%2Fwww.linkedin.com%2Fin%2Fhedyeh-ahmadi__%3B!!LIr3w8kk_Xxm! \
> > > owK3rp5BYaR9BZh-ZgTlsXIxdM3aebgcexnD7meyFOmfUi7AnsDslFD8XZYGRhYRJxXflAbk6pYGdIIu \
> > > WgI%24&data=05%7C02%7Cd.rizopoulos%40erasmusmc.nl%7Caebf617ef97a430fd59808dc29bc \
> > > 1797%7C526638ba6af34b0fa532a1a511f4ac80%7C0%7C0%7C638431135044815898%7CUnknown%7 \
> > > CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=ygMjmU88ZBOHB6GHbBzmvkOaERIvZz4oisAmezhG06A%3D&reserved=0 \
> > > <https://urldefense.com/v3/__http://www.linkedin.com/in/hedyeh-ahmadi__;!!LIr3w8 \
> > > kk_Xxm!owK3rp5BYaR9BZh-ZgTlsXIxdM3aebgcexnD7meyFOmfUi7AnsDslFD8XZYGRhYRJxXflAbk6pYGdIIuWgI$> \
> > > <https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.co \
> > > m%2Fv3%2F__http%3A%2F%2Fwww.linkedin.com%2Fin%2Fhedyeh-ahmadi__%3B!!LIr3w8kk_Xxm \
> > > !owK3rp5BYaR9BZh-ZgTlsXIxdM3aebgcexnD7meyFOmfUi7AnsDslFD8XZYGRhYRJxXflAbk6pYGdII \
> > > uWgI%24&data=05%7C02%7Cd.rizopoulos%40erasmusmc.nl%7Caebf617ef97a430fd59808dc29b \
> > > c1797%7C526638ba6af34b0fa532a1a511f4ac80%7C0%7C0%7C638431135044821234%7CUnknown% \
> > > 7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D \
> > > %7C0%7C%7C%7C&sdata=FMIbPehAFvXEAYBcP0BcGneyPDg0d41AOF%2B4FBu%2FzqQ%3D&reserved=0 \
> > > > 
> > > 
> > > 
> > > 
> > > 
> > > [[alternative HTML version deleted]]
> > > 
> > > _______________________________________________
> > > R-sig-mixed-models@r-project.org mailing list
> > > https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com \
> > > %2Fv3%2F__https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-sig-mixed-models__ \
> > > %3B!!LIr3w8kk_Xxm!owK3rp5BYaR9BZh-ZgTlsXIxdM3aebgcexnD7meyFOmfUi7AnsDslFD8XZYGRh \
> > > YRJxXflAbk6pYGRRULy-w%24&data=05%7C02%7Cd.rizopoulos%40erasmusmc.nl%7Caebf617ef9 \
> > > 7a430fd59808dc29bc1797%7C526638ba6af34b0fa532a1a511f4ac80%7C0%7C0%7C638431135044 \
> > > 825917%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1ha \
> > > WwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=XXOQQb3Bq2TsD15mA4JLybKm%2FfcunRxP5h4LqfPjibg%3D&reserved=0 \
> > > <https://urldefense.com/v3/__https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-m \
> > > odels__;!!LIr3w8kk_Xxm!owK3rp5BYaR9BZh-ZgTlsXIxdM3aebgcexnD7meyFOmfUi7AnsDslFD8XZYGRhYRJxXflAbk6pYGRRULy-w$>
> > > 
> > 
> > --
> > Dr. Benjamin Bolker
> > Professor, Mathematics & Statistics and Biology, McMaster University
> > Director, School of Computational Science and Engineering
> > Associate chair (graduate, math), Mathematics & Statistics
> > > E-mail is sent at my convenience; I don't expect replies outside of
> > working hours.
> > 
> > _______________________________________________
> > R-sig-mixed-models@r-project.org mailing list
> > https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2 \
> > Fv3%2F__https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-sig-mixed-models__%3B! \
> > !LIr3w8kk_Xxm!owK3rp5BYaR9BZh-ZgTlsXIxdM3aebgcexnD7meyFOmfUi7AnsDslFD8XZYGRhYRJxXf \
> > lAbk6pYGRRULy-w%24&data=05%7C02%7Cd.rizopoulos%40erasmusmc.nl%7Caebf617ef97a430fd5 \
> > 9808dc29bc1797%7C526638ba6af34b0fa532a1a511f4ac80%7C0%7C0%7C638431135044830659%7CU \
> > nknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6M \
> > n0%3D%7C0%7C%7C%7C&sdata=%2BmYtfJH%2BgN0%2F%2F7BU%2BVPYkAJeen7r%2B8XAPHnLttJdywk%3D&reserved=0 \
> > <https://urldefense.com/v3/__https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-mod \
> > els__;!!LIr3w8kk_Xxm!owK3rp5BYaR9BZh-ZgTlsXIxdM3aebgcexnD7meyFOmfUi7AnsDslFD8XZYGRhYRJxXflAbk6pYGRRULy-w$>
> >  
> > [[alternative HTML version deleted]]
> > 
> > _______________________________________________
> > R-sig-mixed-models@r-project.org mailing list
> > https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fm \
> > ailman%2Flistinfo%2Fr-sig-mixed-models&data=05%7C02%7Cd.rizopoulos%40erasmusmc.nl% \
> > 7Caebf617ef97a430fd59808dc29bc1797%7C526638ba6af34b0fa532a1a511f4ac80%7C0%7C0%7C63 \
> > 8431135044835348%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBT \
> > iI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=t4c9TyhKRgr31Q2ENbFuv8gcHZK8wAAfhEtOLGCBG%2FM%3D&reserved=0 \
> > <https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models>
> 
> _______________________________________________
> R-sig-mixed-models@r-project.org mailing list
> https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fmai \
> lman%2Flistinfo%2Fr-sig-mixed-models&data=05%7C02%7Cd.rizopoulos%40erasmusmc.nl%7Cae \
> bf617ef97a430fd59808dc29bc1797%7C526638ba6af34b0fa532a1a511f4ac80%7C0%7C0%7C63843113 \
> 5044840607%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1ha \
> WwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=wsMypblJAp8STHQ28siavAUI5yMVM9JCEEGssnpc2PA%3D&reserved=0 \
> <https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models>
_______________________________________________
R-sig-mixed-models@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

[prev in list] [next in list] [prev in thread] [next in thread] 