Bayes Factors for Mixed Models: a Discussion

Johnny van Doorn; Julia M. Haaf; Angelika M. Stefan; Eric Jan Wagenmakers; Gregory Edward Cox; Clintin P. Davis-Stober; Andrew Heathcote; Daniel W. Heck; Michael Kalish; David Kellen; Dora Matzke; Richard D. Morey; Bruno Nicenboim; Don van Ravenzwaaij; Jeffrey N. Rouder; Daniel J. Schad; Richard M. Shiffrin; Henrik Singmann; Shravan Vasishth; João Veríssimo; Florence Bockting; Suyog Chandramouli; John C. Dunn; Quentin F. Gronau; Maximilian Linde; Sara D. McMullin; Danielle Navarro; Martin Schnuerch; Himanshu Yadav; Frederik Aust

doi:10.1007/s42113-022-00160-3

Bayes Factors for Mixed Models: a Discussion

Johnny van Doorn, Julia M. Haaf, Angelika M. Stefan, Eric Jan Wagenmakers, Gregory Edward Cox, Clintin P. Davis-Stober, Andrew Heathcote, Daniel W. Heck, Michael Kalish, David Kellen, Dora Matzke, Richard D. Morey, Bruno Nicenboim, Don van Ravenzwaaij, Jeffrey N. Rouder, Daniel J. Schad, Richard M. Shiffrin, Henrik Singmann, Shravan Vasishth, João VeríssimoFlorence Bockting, Suyog Chandramouli, John C. Dunn, Quentin F. Gronau, Maximilian Linde, Sara D. McMullin, Danielle Navarro, Martin Schnuerch, Himanshu Yadav, Frederik Aust

Research output: Contribution to journal › Article › peer-review

Abstract

van Doorn et al. (2021) outlined various questions that arise when conducting Bayesian model comparison for mixed effects models. Seven response articles offered their own perspective on the preferred setup for mixed model comparison, on the most appropriate specification of prior distributions, and on the desirability of default recommendations. This article presents a round-table discussion that aims to clarify outstanding issues, explore common ground, and outline practical considerations for any researcher wishing to conduct a Bayesian mixed effects model comparison.

Original language	English (US)
Pages (from-to)	140-158
Number of pages	19
Journal	Computational Brain and Behavior
Volume	6
Issue number	1
DOIs	https://doi.org/10.1007/s42113-022-00160-3
State	Published - Mar 2023

Keywords

Bayes factors
Mixed effects
Mixed models
Random effects

ASJC Scopus subject areas

Neuropsychology and Physiological Psychology
Developmental and Educational Psychology

Access to Document

10.1007/s42113-022-00160-3

Cite this

van Doorn, J., Haaf, J. M., Stefan, A. M., Wagenmakers, E. J., Cox, G. E., Davis-Stober, C. P., Heathcote, A., Heck, D. W., Kalish, M., Kellen, D., Matzke, D., Morey, R. D., Nicenboim, B., van Ravenzwaaij, D., Rouder, J. N., Schad, D. J., Shiffrin, R. M., Singmann, H., Vasishth, S., ... Aust, F. (2023). Bayes Factors for Mixed Models: a Discussion. Computational Brain and Behavior, 6(1), 140-158. https://doi.org/10.1007/s42113-022-00160-3

van Doorn, J, Haaf, JM, Stefan, AM, Wagenmakers, EJ, Cox, GE, Davis-Stober, CP, Heathcote, A, Heck, DW, Kalish, M , Kellen, D, Matzke, D, Morey, RD, Nicenboim, B, van Ravenzwaaij, D, Rouder, JN, Schad, DJ, Shiffrin, RM, Singmann, H, Vasishth, S, Veríssimo, J, Bockting, F, Chandramouli, S, Dunn, JC, Gronau, QF, Linde, M, McMullin, SD, Navarro, D, Schnuerch, M, Yadav, H & Aust, F 2023, 'Bayes Factors for Mixed Models: a Discussion', Computational Brain and Behavior, vol. 6, no. 1, pp. 140-158. https://doi.org/10.1007/s42113-022-00160-3

@article{e811a57ff8e146ff8787b7311d4c8f5d,

title = "Bayes Factors for Mixed Models: a Discussion",

abstract = "van Doorn et al. (2021) outlined various questions that arise when conducting Bayesian model comparison for mixed effects models. Seven response articles offered their own perspective on the preferred setup for mixed model comparison, on the most appropriate specification of prior distributions, and on the desirability of default recommendations. This article presents a round-table discussion that aims to clarify outstanding issues, explore common ground, and outline practical considerations for any researcher wishing to conduct a Bayesian mixed effects model comparison.",

keywords = "Bayes factors, Mixed effects, Mixed models, Random effects",

author = "{van Doorn}, Johnny and Haaf, {Julia M.} and Stefan, {Angelika M.} and Wagenmakers, {Eric Jan} and Cox, {Gregory Edward} and Davis-Stober, {Clintin P.} and Andrew Heathcote and Heck, {Daniel W.} and Michael Kalish and David Kellen and Dora Matzke and Morey, {Richard D.} and Bruno Nicenboim and {van Ravenzwaaij}, Don and Rouder, {Jeffrey N.} and Schad, {Daniel J.} and Shiffrin, {Richard M.} and Henrik Singmann and Shravan Vasishth and Jo{\~a}o Ver{\'i}ssimo and Florence Bockting and Suyog Chandramouli and Dunn, {John C.} and Gronau, {Quentin F.} and Maximilian Linde and McMullin, {Sara D.} and Danielle Navarro and Martin Schnuerch and Himanshu Yadav and Frederik Aust",

note = "Funding Information: This work was supported in part by a Vici grant from the Netherlands Organization of Scientific Research (NWO) awarded to EJW (016.Vici.170.083), an NWO Research Talent grant to AMS (406.18.556), a Veni grant from the NWO (VI.Veni.201G.019) to JMH, an Advanced ERC grant to EJW (743086 UNIFY), a NSF CAREER Award awarded to DK (ID 2145308), a Vidi grant from the Netherlands Organization of Scientific Research (NWO) awarded to DM (VI.Vidi.191.091) and DvR (016.Vidi.188.001). JV and SV were partly funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - Project ID 317633480 - SFB 1287, and JV was partly funded by the Foundation for Science and Technology Portugal (UIDB/00214/2020). Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = mar,

doi = "10.1007/s42113-022-00160-3",

language = "English (US)",

volume = "6",

pages = "140--158",

journal = "Computational Brain and Behavior",

issn = "2522-087X",

publisher = "Springer Nature",

number = "1",

}

TY - JOUR

T1 - Bayes Factors for Mixed Models

T2 - a Discussion

AU - van Doorn, Johnny

AU - Haaf, Julia M.

AU - Stefan, Angelika M.

AU - Wagenmakers, Eric Jan

AU - Cox, Gregory Edward

AU - Davis-Stober, Clintin P.

AU - Heathcote, Andrew

AU - Heck, Daniel W.

AU - Kalish, Michael

AU - Kellen, David

AU - Matzke, Dora

AU - Morey, Richard D.

AU - Nicenboim, Bruno

AU - van Ravenzwaaij, Don

AU - Rouder, Jeffrey N.

AU - Schad, Daniel J.

AU - Shiffrin, Richard M.

AU - Singmann, Henrik

AU - Vasishth, Shravan

AU - Veríssimo, João

AU - Bockting, Florence

AU - Chandramouli, Suyog

AU - Dunn, John C.

AU - Gronau, Quentin F.

AU - Linde, Maximilian

AU - McMullin, Sara D.

AU - Navarro, Danielle

AU - Schnuerch, Martin

AU - Yadav, Himanshu

AU - Aust, Frederik

N1 - Funding Information: This work was supported in part by a Vici grant from the Netherlands Organization of Scientific Research (NWO) awarded to EJW (016.Vici.170.083), an NWO Research Talent grant to AMS (406.18.556), a Veni grant from the NWO (VI.Veni.201G.019) to JMH, an Advanced ERC grant to EJW (743086 UNIFY), a NSF CAREER Award awarded to DK (ID 2145308), a Vidi grant from the Netherlands Organization of Scientific Research (NWO) awarded to DM (VI.Vidi.191.091) and DvR (016.Vidi.188.001). JV and SV were partly funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - Project ID 317633480 - SFB 1287, and JV was partly funded by the Foundation for Science and Technology Portugal (UIDB/00214/2020). Publisher Copyright: © 2023, The Author(s).

PY - 2023/3

Y1 - 2023/3

N2 - van Doorn et al. (2021) outlined various questions that arise when conducting Bayesian model comparison for mixed effects models. Seven response articles offered their own perspective on the preferred setup for mixed model comparison, on the most appropriate specification of prior distributions, and on the desirability of default recommendations. This article presents a round-table discussion that aims to clarify outstanding issues, explore common ground, and outline practical considerations for any researcher wishing to conduct a Bayesian mixed effects model comparison.

AB - van Doorn et al. (2021) outlined various questions that arise when conducting Bayesian model comparison for mixed effects models. Seven response articles offered their own perspective on the preferred setup for mixed model comparison, on the most appropriate specification of prior distributions, and on the desirability of default recommendations. This article presents a round-table discussion that aims to clarify outstanding issues, explore common ground, and outline practical considerations for any researcher wishing to conduct a Bayesian mixed effects model comparison.

KW - Bayes factors

KW - Mixed effects

KW - Mixed models

KW - Random effects

UR - http://www.scopus.com/inward/record.url?scp=85148050348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85148050348&partnerID=8YFLogxK

U2 - 10.1007/s42113-022-00160-3

DO - 10.1007/s42113-022-00160-3

M3 - Article

AN - SCOPUS:85148050348

SN - 2522-087X

VL - 6

SP - 140

EP - 158

JO - Computational Brain and Behavior

JF - Computational Brain and Behavior

IS - 1

ER -

Bayes Factors for Mixed Models: a Discussion

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this