glmmTMB Balances Speed and Flexibility Among Packages for Zero-inflated Generalized Linear Mixed Modeling

Published on Jan 1, 2017in R Journal2.68
· DOI :10.32614/RJ-2017-066
Mollie E. Brooks7
Estimated H-index: 7
Kasper Kristensen14
Estimated H-index: 14
+ 6 AuthorsBenjamin M. Bolker46
Estimated H-index: 46
(McMaster University)
View in Source
Count data can be analyzed using generalized linear mixed models when observations are correlated in ways that require random effects. However, count data are often zero-inflated, containing more zeros than would be expected from the typical error distributions. We present a new package, glmmTMB, and compare it to other R packages that fit zero-inflated mixed models. The glmmTMB package fits many types of GLMMs and extensions, including models with continuously distributed responses, but here we focus on count responses. glmmTMB is faster than glmmADMB, MCMCglmm, and brms, and more flexible than INLA and mgcv for zero-inflated modeling. One unique feature of glmmTMB (among packages that fit zero-inflated mixed models) is its ability to estimate the Conway-Maxwell-Poisson distribution parameterized by the mean. Overall, its most appealing features for new users may be the combination of speed, flexibility, and its interface’s similarity to lme4.
  • References (0)
  • Citations (186)
Cited By186
#1Sebastian Kolb (University of Koblenz and Landau)H-Index: 1
#2Deniz UzmanH-Index: 2
Last.Martin H. Entling (University of Koblenz and Landau)H-Index: 19
view all 5 authors...
#1Jesse Whittington (Parks Canada)H-Index: 15
#2Petah Low (Parks Canada)H-Index: 1
Last.Bill Hunt (Parks Canada)H-Index: 2
view all 3 authors...
1 CitationsSource
#1Beatriz Diaz Pauli (University of Oslo)H-Index: 4
#2Sarah Garric (Paris Diderot University)
Last.Eric Edeline (Paris Diderot University)H-Index: 2
view all 5 authors...
#1Aline S. Martinez (UNSW: University of New South Wales)
#2Mariana Mayer-Pinto (UNSW: University of New South Wales)H-Index: 13
Last.Ronaldo Adriano Christofoletti (UNIFESP: Federal University of São Paulo)H-Index: 11
view all 3 authors...
#1Christopher A. Gaulke (OSU: Oregon State University)H-Index: 4
#2Maurício Laterça Martins (UFSC: Universidade Federal de Santa Catarina)H-Index: 27
Last.Thomas J. Sharpton (OSU: Oregon State University)H-Index: 19
view all 7 authors...
3 CitationsSource
#1Maximiliano Tourmente (University of Exeter)H-Index: 14
#2C. Ruth Archer (University of Exeter)H-Index: 8
Last.David J. Hosken (University of Exeter)H-Index: 47
view all 3 authors...
#1Michael Li (McMaster University)H-Index: 4
#2Benjamin M. Bolker (McMaster University)H-Index: 46
Last.David J. D. Earn (McMaster University)H-Index: 34
view all 5 authors...
#1Ingrid S. Tarr (Macquarie University)H-Index: 2
#2Emily P. McCann (Macquarie University)H-Index: 9
Last.Kelly L. Williams (Macquarie University)H-Index: 20
view all 14 authors...
2 CitationsSource
#1Valentina Ferretti (Facultad de Ciencias Exactas y Naturales)H-Index: 9
#2Viviana Massoni (Facultad de Ciencias Exactas y Naturales)H-Index: 9
Last.David W. Winkler (Cornell University)H-Index: 47
view all 5 authors...
#1Haneul Jang (MPG: Max Planck Society)H-Index: 1
#2Christophe Boesch (MPG: Max Planck Society)H-Index: 81
Last.Karline R. L. Janmaat (MPG: Max Planck Society)H-Index: 12
view all 5 authors...
2 CitationsSource
View next paperFitting Linear Mixed-Effects Models Using lme4