SlideShare a Scribd company logo
Denitions Statistics Computation Sociological Conclusions References
General-purpose tools
for generalized linear mixed models
Ben Bolker
McMaster University, Mathematics  Statistics and Biology
13 September 2013
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Outline
1 Denitions and context
2 Statistical challenges
3 Computational challenges
4 Sociological challenges
5 Conclusions
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Outline
1 Denitions and context
2 Statistical challenges
3 Computational challenges
4 Sociological challenges
5 Conclusions
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Generalized linear mixed models
GLMMs: a statistical modeling framework incorporating:
Linear combinations of categorical and continuous
predictors, and interactions
Response distributions in the exponential family
(binomial, Poisson, and extensions)
Any smooth, monotonic link function
(e.g. logistic, exponential models)
Flexible combinations of blocking factors
(clustering; random eects)
Applications in ecology, neurobiology, behaviour, epidemiology, real
estate, . . .
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Generalized linear mixed models
GLMMs: a statistical modeling framework incorporating:
Linear combinations of categorical and continuous
predictors, and interactions
Response distributions in the exponential family
(binomial, Poisson, and extensions)
Any smooth, monotonic link function
(e.g. logistic, exponential models)
Flexible combinations of blocking factors
(clustering; random eects)
Applications in ecology, neurobiology, behaviour, epidemiology, real
estate, . . .
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Generalized linear mixed models
GLMMs: a statistical modeling framework incorporating:
Linear combinations of categorical and continuous
predictors, and interactions
Response distributions in the exponential family
(binomial, Poisson, and extensions)
Any smooth, monotonic link function
(e.g. logistic, exponential models)
Flexible combinations of blocking factors
(clustering; random eects)
Applications in ecology, neurobiology, behaviour, epidemiology, real
estate, . . .
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Generalized linear mixed models
GLMMs: a statistical modeling framework incorporating:
Linear combinations of categorical and continuous
predictors, and interactions
Response distributions in the exponential family
(binomial, Poisson, and extensions)
Any smooth, monotonic link function
(e.g. logistic, exponential models)
Flexible combinations of blocking factors
(clustering; random eects)
Applications in ecology, neurobiology, behaviour, epidemiology, real
estate, . . .
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Technical denition
Yi
response
∼
conditional
distribution
Distr (g
−1(ηi )
inverse
link
function
, φ
scale
parameter
)
η
linear
predictor
= Xβ
xed
eects
+ Zb
random
eects
b
conditional
modes
∼ MVN(0, Σ(θ)
variance-
covariance
matrix
)
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Outline
1 Denitions and context
2 Statistical challenges
3 Computational challenges
4 Sociological challenges
5 Conclusions
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Estimation
Maximum likelihood estimation
L(Yi |θ, β)
likelihood
= · · · L(Yi |θ, β )
data|random eects
× L(β |Σ(θ))
random eects
dβ
deterministic: precision vs. computational cost:
penalized quasi-likelihood, Laplace approximation, adaptive
Gauss-Hermite quadrature (Breslow, 2004) . . .
Monte Carlo: frequentist and Bayesian (Booth and Hobert,
1999; Ponciano et al., 2009; Sung, 2007)
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Estimation: example (McKeon et al., 2012)
Log−odds of predation
−6 −4 −2 0 2
Symbiont
Crab vs. Shrimp
Added symbiont
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
GLM (fixed)
GLM (pooled)
PQL
Laplace
AGQ
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Inference
Big problem.
Inferential tools: either asymptotic
or taken from classical linear
models
boundary solutions (Stram and
Lee, 1994)
the great p-value/degrees of
freedom debate
small numbers of clusters
solutions: computational
and/or Bayesian
(parametric bootstrap, MCMC)
True p value
Inferredpvalue
0.02
0.04
0.06
0.08
0.02 0.06
Osm Cu
H2S
0.02 0.06
0.02
0.04
0.06
0.08
Anoxia
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Outline
1 Denitions and context
2 Statistical challenges
3 Computational challenges
4 Sociological challenges
5 Conclusions
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Sparse matrix algorithms
repeated decomposition of
large, matrices (especially Z)
ll-reducing permutation to
improve sparsity pattern
further improvements possible:
better matrix representation,
parallelization?
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Bounded optimization
Parameterize
variance-covariance matrix Σ(θ)
(Pinheiro and Bates, 1996)
Positive denite or only
semi-denite?
Disadvantages of transforming
to unconstrain
(Disadvantages of boundary
solutions)
raw log
0
10
20
30
0 1 2 3 −3 −2 −1 0
deviance
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Outline
1 Denitions and context
2 Statistical challenges
3 Computational challenges
4 Sociological challenges
5 Conclusions
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Sociological issues
The curse of neophilia
Wide user base:
As usual when software for complicated statistical
inference procedures is broadly disseminated, there is
potential for abuse and misinterpretation.
(Breslow, 2004)
What if there is no good answer?
do no harm vs. better me than someone else
Diagnostics and warning messages
End users vs. downstream developers
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Outline
1 Denitions and context
2 Statistical challenges
3 Computational challenges
4 Sociological challenges
5 Conclusions
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Next steps
Alternative platforms/languages
Flexible correlation structures:
spatial, temporal, phylogenetic . . .
Improved MCMC methods?
Simulation tests of inferential tools (sigh)
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Is it science?
Science is what we
understand well enough to
explain to a computer. Art
is everything else we do.
(Donald Knuth)
10
20
30
40
50
2006 2008 2010 2012
Date
articlespermonth
key
glmm
lme4
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Acknowledgments
lme4: Doug Bates, Martin
Mächler, Steve Walker
Data: Adrian Stier (UBC/OSU),
Sea McKeon (Smithsonian),
David Julian (UF)
NSERC (Discovery)
SHARCnet
Ben Bolker
GLMMs
Denitions Statistics Computation Sociological Conclusions References
Booth, J.G. and Hobert, J.P., 1999. Journal of the Royal Statistical Society. Series B, 61(1):265285.
doi:10.1111/1467-9868.00176.
Breslow, N.E., 2004. In D.Y. Lin and P.J. Heagerty, editors, Proceedings of the second Seattle
symposium in biostatistics: Analysis of correlated data, pages 122. Springer. ISBN 0387208623.
McKeon, C.S., Stier, A., et al., 2012. Oecologia, 169(4):10951103. ISSN 0029-8549.
doi:10.1007/s00442-012-2275-2.
Pinheiro, J.C. and Bates, D.M., 1996. Statistics and Computing, 6(3):289296.
doi:10.1007/BF00140873.
Ponciano, J.M., Taper, M.L., et al., 2009. Ecology, 90(2):356362. ISSN 0012-9658.
Stram, D.O. and Lee, J.W., 1994. Biometrics, 50(4):11711177.
Sung, Y.J., 2007. The Annals of Statistics, 35(3):9901011. ISSN 0090-5364.
doi:10.1214/009053606000001389.
Ben Bolker
GLMMs

More Related Content

What's hot

IUI 2016 Presentation Slide
IUI 2016 Presentation SlideIUI 2016 Presentation Slide
IUI 2016 Presentation Slide
University of Central Florida
 
Consideration on Fairness-aware Data Mining
Consideration on Fairness-aware Data MiningConsideration on Fairness-aware Data Mining
Consideration on Fairness-aware Data Mining
Toshihiro Kamishima
 
Parametric Sensitivity Analysis of a Mathematical Model of Two Interacting Po...
Parametric Sensitivity Analysis of a Mathematical Model of Two Interacting Po...Parametric Sensitivity Analysis of a Mathematical Model of Two Interacting Po...
Parametric Sensitivity Analysis of a Mathematical Model of Two Interacting Po...
IOSR Journals
 

What's hot (6)

PresTrojan0_1212
PresTrojan0_1212PresTrojan0_1212
PresTrojan0_1212
 
IUI 2016 Presentation Slide
IUI 2016 Presentation SlideIUI 2016 Presentation Slide
IUI 2016 Presentation Slide
 
Digit Span Lab
Digit Span LabDigit Span Lab
Digit Span Lab
 
Consideration on Fairness-aware Data Mining
Consideration on Fairness-aware Data MiningConsideration on Fairness-aware Data Mining
Consideration on Fairness-aware Data Mining
 
Parametric Sensitivity Analysis of a Mathematical Model of Two Interacting Po...
Parametric Sensitivity Analysis of a Mathematical Model of Two Interacting Po...Parametric Sensitivity Analysis of a Mathematical Model of Two Interacting Po...
Parametric Sensitivity Analysis of a Mathematical Model of Two Interacting Po...
 
Chapter 11 Psrm
Chapter 11 PsrmChapter 11 Psrm
Chapter 11 Psrm
 

Viewers also liked

evolution of virulence: devil in the details
evolution of virulence: devil in the detailsevolution of virulence: devil in the details
evolution of virulence: devil in the details
Ben Bolker
 
Davis eco-evo virulence
Davis eco-evo virulenceDavis eco-evo virulence
Davis eco-evo virulenceBen Bolker
 
math bio for 1st year math students
math bio for 1st year math studentsmath bio for 1st year math students
math bio for 1st year math students
Ben Bolker
 
model complexity and model choice for animal movement models
model complexity and model choice for animal movement modelsmodel complexity and model choice for animal movement models
model complexity and model choice for animal movement models
Ben Bolker
 
Bolker esa2014
Bolker esa2014Bolker esa2014
Bolker esa2014
Ben Bolker
 
ESS of minimal mutation rate in an evo-epidemiological model
ESS of minimal mutation rate in an evo-epidemiological modelESS of minimal mutation rate in an evo-epidemiological model
ESS of minimal mutation rate in an evo-epidemiological model
Ben Bolker
 
virulence evolution (IGERT symposium)
virulence evolution (IGERT symposium)virulence evolution (IGERT symposium)
virulence evolution (IGERT symposium)Ben Bolker
 
Waterloo GLMM talk
Waterloo GLMM talkWaterloo GLMM talk
Waterloo GLMM talk
Ben Bolker
 
intro to knitr with RStudio
intro to knitr with RStudiointro to knitr with RStudio
intro to knitr with RStudioBen Bolker
 
model complexity and model choice for animal movement models
model complexity and model choice for animal movement modelsmodel complexity and model choice for animal movement models
model complexity and model choice for animal movement models
Ben Bolker
 

Viewers also liked (12)

evolution of virulence: devil in the details
evolution of virulence: devil in the detailsevolution of virulence: devil in the details
evolution of virulence: devil in the details
 
Davis eco-evo virulence
Davis eco-evo virulenceDavis eco-evo virulence
Davis eco-evo virulence
 
math bio for 1st year math students
math bio for 1st year math studentsmath bio for 1st year math students
math bio for 1st year math students
 
model complexity and model choice for animal movement models
model complexity and model choice for animal movement modelsmodel complexity and model choice for animal movement models
model complexity and model choice for animal movement models
 
Bolker esa2014
Bolker esa2014Bolker esa2014
Bolker esa2014
 
ESS of minimal mutation rate in an evo-epidemiological model
ESS of minimal mutation rate in an evo-epidemiological modelESS of minimal mutation rate in an evo-epidemiological model
ESS of minimal mutation rate in an evo-epidemiological model
 
virulence evolution (IGERT symposium)
virulence evolution (IGERT symposium)virulence evolution (IGERT symposium)
virulence evolution (IGERT symposium)
 
Waterloo GLMM talk
Waterloo GLMM talkWaterloo GLMM talk
Waterloo GLMM talk
 
Threads 2013
Threads 2013Threads 2013
Threads 2013
 
Google lme4
Google lme4Google lme4
Google lme4
 
intro to knitr with RStudio
intro to knitr with RStudiointro to knitr with RStudio
intro to knitr with RStudio
 
model complexity and model choice for animal movement models
model complexity and model choice for animal movement modelsmodel complexity and model choice for animal movement models
model complexity and model choice for animal movement models
 

Similar to Threads 2013

Open source GLMM tools: Concordia
Open source GLMM tools: ConcordiaOpen source GLMM tools: Concordia
Open source GLMM tools: Concordia
Ben Bolker
 
MS-Intro.pptx
MS-Intro.pptxMS-Intro.pptx
MS-Intro.pptx
ShriramKargaonkar
 
M.E.Bontempi-Panel data: Models, estimation,and the role of attrition and Mea...
M.E.Bontempi-Panel data: Models, estimation,and the role of attrition and Mea...M.E.Bontempi-Panel data: Models, estimation,and the role of attrition and Mea...
M.E.Bontempi-Panel data: Models, estimation,and the role of attrition and Mea...
Istituto nazionale di statistica
 
Diminishing Returns: When Should Real- world Surveys Stop Sampling?
Diminishing Returns: When Should Real- world Surveys Stop Sampling?Diminishing Returns: When Should Real- world Surveys Stop Sampling?
Diminishing Returns: When Should Real- world Surveys Stop Sampling?
Inspirient
 
Pittsburgh and Toronto "Halloween US trip" seminars
Pittsburgh and Toronto "Halloween US trip" seminarsPittsburgh and Toronto "Halloween US trip" seminars
Pittsburgh and Toronto "Halloween US trip" seminars
Christian Robert
 
slides of ABC talk at i-like workshop, Warwick, May 16
slides of ABC talk at i-like workshop, Warwick, May 16slides of ABC talk at i-like workshop, Warwick, May 16
slides of ABC talk at i-like workshop, Warwick, May 16
Christian Robert
 
Social Learning in Networks: Extraction Deterministic Rules
Social Learning in Networks: Extraction Deterministic RulesSocial Learning in Networks: Extraction Deterministic Rules
Social Learning in Networks: Extraction Deterministic Rules
Dmitrii Ignatov
 
Sociological classifications and simulation models of social inequality
Sociological classifications and simulation models of social inequalitySociological classifications and simulation models of social inequality
Sociological classifications and simulation models of social inequality
NeISSProject
 
02. predicting financial distress logit mode jones
02. predicting financial distress logit mode jones02. predicting financial distress logit mode jones
02. predicting financial distress logit mode jones
Sailendra Nangadam
 
What is statistics
What is statisticsWhat is statistics
What is statistics
Dr. Stylianos Kampakis
 
Linear models for data science
Linear models for data scienceLinear models for data science
Linear models for data science
Brad Klingenberg
 
Investigations of certain estimators for modeling panel data under violations...
Investigations of certain estimators for modeling panel data under violations...Investigations of certain estimators for modeling panel data under violations...
Investigations of certain estimators for modeling panel data under violations...Alexander Decker
 
Intro to Model Selection
Intro to Model SelectionIntro to Model Selection
Intro to Model Selectionchenhm
 
ISBA 2022 Susie Bayarri lecture
ISBA 2022 Susie Bayarri lectureISBA 2022 Susie Bayarri lecture
ISBA 2022 Susie Bayarri lecture
Pierre Jacob
 
Topics in-survey-methologogy-and-survey-analysis-kimmo-vehkalahti-2013
Topics in-survey-methologogy-and-survey-analysis-kimmo-vehkalahti-2013Topics in-survey-methologogy-and-survey-analysis-kimmo-vehkalahti-2013
Topics in-survey-methologogy-and-survey-analysis-kimmo-vehkalahti-2013
Kimmo Vehkalahti
 
Can We Use Rum and Not Get Drunk?
Can We Use Rum and Not Get Drunk?Can We Use Rum and Not Get Drunk?
Can We Use Rum and Not Get Drunk?
Jorge Araña
 
[A]BCel : a presentation at ABC in Roma
[A]BCel : a presentation at ABC in Roma[A]BCel : a presentation at ABC in Roma
[A]BCel : a presentation at ABC in Roma
Christian Robert
 
The Power of Topology - Colleen Farrelly - WiDS Miami 2018
The Power of Topology - Colleen Farrelly - WiDS Miami 2018The Power of Topology - Colleen Farrelly - WiDS Miami 2018
The Power of Topology - Colleen Farrelly - WiDS Miami 2018
Catalina Arango
 
Women in Data Science 2018 Slides--Small Samples, Subgroups, and Topology
Women in Data Science 2018 Slides--Small Samples, Subgroups, and TopologyWomen in Data Science 2018 Slides--Small Samples, Subgroups, and Topology
Women in Data Science 2018 Slides--Small Samples, Subgroups, and Topology
Colleen Farrelly
 

Similar to Threads 2013 (20)

Open source GLMM tools: Concordia
Open source GLMM tools: ConcordiaOpen source GLMM tools: Concordia
Open source GLMM tools: Concordia
 
MS-Intro.pptx
MS-Intro.pptxMS-Intro.pptx
MS-Intro.pptx
 
M.E.Bontempi-Panel data: Models, estimation,and the role of attrition and Mea...
M.E.Bontempi-Panel data: Models, estimation,and the role of attrition and Mea...M.E.Bontempi-Panel data: Models, estimation,and the role of attrition and Mea...
M.E.Bontempi-Panel data: Models, estimation,and the role of attrition and Mea...
 
Diminishing Returns: When Should Real- world Surveys Stop Sampling?
Diminishing Returns: When Should Real- world Surveys Stop Sampling?Diminishing Returns: When Should Real- world Surveys Stop Sampling?
Diminishing Returns: When Should Real- world Surveys Stop Sampling?
 
Pittsburgh and Toronto "Halloween US trip" seminars
Pittsburgh and Toronto "Halloween US trip" seminarsPittsburgh and Toronto "Halloween US trip" seminars
Pittsburgh and Toronto "Halloween US trip" seminars
 
slides of ABC talk at i-like workshop, Warwick, May 16
slides of ABC talk at i-like workshop, Warwick, May 16slides of ABC talk at i-like workshop, Warwick, May 16
slides of ABC talk at i-like workshop, Warwick, May 16
 
Social Learning in Networks: Extraction Deterministic Rules
Social Learning in Networks: Extraction Deterministic RulesSocial Learning in Networks: Extraction Deterministic Rules
Social Learning in Networks: Extraction Deterministic Rules
 
Sociological classifications and simulation models of social inequality
Sociological classifications and simulation models of social inequalitySociological classifications and simulation models of social inequality
Sociological classifications and simulation models of social inequality
 
02. predicting financial distress logit mode jones
02. predicting financial distress logit mode jones02. predicting financial distress logit mode jones
02. predicting financial distress logit mode jones
 
What is statistics
What is statisticsWhat is statistics
What is statistics
 
Linear models for data science
Linear models for data scienceLinear models for data science
Linear models for data science
 
Investigations of certain estimators for modeling panel data under violations...
Investigations of certain estimators for modeling panel data under violations...Investigations of certain estimators for modeling panel data under violations...
Investigations of certain estimators for modeling panel data under violations...
 
Intro to Model Selection
Intro to Model SelectionIntro to Model Selection
Intro to Model Selection
 
ISBA 2022 Susie Bayarri lecture
ISBA 2022 Susie Bayarri lectureISBA 2022 Susie Bayarri lecture
ISBA 2022 Susie Bayarri lecture
 
Topics in-survey-methologogy-and-survey-analysis-kimmo-vehkalahti-2013
Topics in-survey-methologogy-and-survey-analysis-kimmo-vehkalahti-2013Topics in-survey-methologogy-and-survey-analysis-kimmo-vehkalahti-2013
Topics in-survey-methologogy-and-survey-analysis-kimmo-vehkalahti-2013
 
Can We Use Rum and Not Get Drunk?
Can We Use Rum and Not Get Drunk?Can We Use Rum and Not Get Drunk?
Can We Use Rum and Not Get Drunk?
 
ECONOMETRICS I ASA
ECONOMETRICS I ASAECONOMETRICS I ASA
ECONOMETRICS I ASA
 
[A]BCel : a presentation at ABC in Roma
[A]BCel : a presentation at ABC in Roma[A]BCel : a presentation at ABC in Roma
[A]BCel : a presentation at ABC in Roma
 
The Power of Topology - Colleen Farrelly - WiDS Miami 2018
The Power of Topology - Colleen Farrelly - WiDS Miami 2018The Power of Topology - Colleen Farrelly - WiDS Miami 2018
The Power of Topology - Colleen Farrelly - WiDS Miami 2018
 
Women in Data Science 2018 Slides--Small Samples, Subgroups, and Topology
Women in Data Science 2018 Slides--Small Samples, Subgroups, and TopologyWomen in Data Science 2018 Slides--Small Samples, Subgroups, and Topology
Women in Data Science 2018 Slides--Small Samples, Subgroups, and Topology
 

More from Ben Bolker

Ecological synthesis across scales: West Nile virus in individuals and commun...
Ecological synthesis across scales: West Nile virus in individuals and commun...Ecological synthesis across scales: West Nile virus in individuals and commun...
Ecological synthesis across scales: West Nile virus in individuals and commun...
Ben Bolker
 
Fundamental principles (?) of biological data
Fundamental principles (?) of biological dataFundamental principles (?) of biological data
Fundamental principles (?) of biological data
Ben Bolker
 
MBRS detectability talk
MBRS detectability talkMBRS detectability talk
MBRS detectability talkBen Bolker
 
Disease-induced extinction
Disease-induced extinctionDisease-induced extinction
Disease-induced extinction
Ben Bolker
 
Zif bolker_w2
Zif bolker_w2Zif bolker_w2
Zif bolker_w2
Ben Bolker
 
Trondheim glmm
Trondheim glmmTrondheim glmm
Trondheim glmm
Ben Bolker
 
MBI intro to spatial models
MBI intro to spatial modelsMBI intro to spatial models
MBI intro to spatial modelsBen Bolker
 
Harvard Forest GLMM talk
Harvard Forest GLMM talkHarvard Forest GLMM talk
Harvard Forest GLMM talkBen Bolker
 
ESA 2011 pines/spatial talk
ESA 2011 pines/spatial talkESA 2011 pines/spatial talk
ESA 2011 pines/spatial talkBen Bolker
 
open-source GLMM tools
open-source GLMM toolsopen-source GLMM tools
open-source GLMM tools
Ben Bolker
 
unmarked individuals: Guelph
unmarked individuals: Guelphunmarked individuals: Guelph
unmarked individuals: GuelphBen Bolker
 
GLMs and extensions in R
GLMs and extensions in RGLMs and extensions in R
GLMs and extensions in R
Ben Bolker
 

More from Ben Bolker (12)

Ecological synthesis across scales: West Nile virus in individuals and commun...
Ecological synthesis across scales: West Nile virus in individuals and commun...Ecological synthesis across scales: West Nile virus in individuals and commun...
Ecological synthesis across scales: West Nile virus in individuals and commun...
 
Fundamental principles (?) of biological data
Fundamental principles (?) of biological dataFundamental principles (?) of biological data
Fundamental principles (?) of biological data
 
MBRS detectability talk
MBRS detectability talkMBRS detectability talk
MBRS detectability talk
 
Disease-induced extinction
Disease-induced extinctionDisease-induced extinction
Disease-induced extinction
 
Zif bolker_w2
Zif bolker_w2Zif bolker_w2
Zif bolker_w2
 
Trondheim glmm
Trondheim glmmTrondheim glmm
Trondheim glmm
 
MBI intro to spatial models
MBI intro to spatial modelsMBI intro to spatial models
MBI intro to spatial models
 
Harvard Forest GLMM talk
Harvard Forest GLMM talkHarvard Forest GLMM talk
Harvard Forest GLMM talk
 
ESA 2011 pines/spatial talk
ESA 2011 pines/spatial talkESA 2011 pines/spatial talk
ESA 2011 pines/spatial talk
 
open-source GLMM tools
open-source GLMM toolsopen-source GLMM tools
open-source GLMM tools
 
unmarked individuals: Guelph
unmarked individuals: Guelphunmarked individuals: Guelph
unmarked individuals: Guelph
 
GLMs and extensions in R
GLMs and extensions in RGLMs and extensions in R
GLMs and extensions in R
 

Recently uploaded

Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
James Anderson
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
Vlad Stirbu
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
sonjaschweigert1
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
Sri Ambati
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
SOFTTECHHUB
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
RinaMondal9
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
Alpen-Adria-Universität
 
Enhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZEnhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZ
Globus
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
UiPathCommunity
 

Recently uploaded (20)

Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
 
Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
Why You Should Replace Windows 11 with Nitrux Linux 3.5.0 for enhanced perfor...
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
 
Video Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the FutureVideo Streaming: Then, Now, and in the Future
Video Streaming: Then, Now, and in the Future
 
Enhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZEnhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZ
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
 

Threads 2013

  • 1. Denitions Statistics Computation Sociological Conclusions References General-purpose tools for generalized linear mixed models Ben Bolker McMaster University, Mathematics Statistics and Biology 13 September 2013 Ben Bolker GLMMs
  • 2. Denitions Statistics Computation Sociological Conclusions References Outline 1 Denitions and context 2 Statistical challenges 3 Computational challenges 4 Sociological challenges 5 Conclusions Ben Bolker GLMMs
  • 3. Denitions Statistics Computation Sociological Conclusions References Outline 1 Denitions and context 2 Statistical challenges 3 Computational challenges 4 Sociological challenges 5 Conclusions Ben Bolker GLMMs
  • 4. Denitions Statistics Computation Sociological Conclusions References Generalized linear mixed models GLMMs: a statistical modeling framework incorporating: Linear combinations of categorical and continuous predictors, and interactions Response distributions in the exponential family (binomial, Poisson, and extensions) Any smooth, monotonic link function (e.g. logistic, exponential models) Flexible combinations of blocking factors (clustering; random eects) Applications in ecology, neurobiology, behaviour, epidemiology, real estate, . . . Ben Bolker GLMMs
  • 5. Denitions Statistics Computation Sociological Conclusions References Generalized linear mixed models GLMMs: a statistical modeling framework incorporating: Linear combinations of categorical and continuous predictors, and interactions Response distributions in the exponential family (binomial, Poisson, and extensions) Any smooth, monotonic link function (e.g. logistic, exponential models) Flexible combinations of blocking factors (clustering; random eects) Applications in ecology, neurobiology, behaviour, epidemiology, real estate, . . . Ben Bolker GLMMs
  • 6. Denitions Statistics Computation Sociological Conclusions References Generalized linear mixed models GLMMs: a statistical modeling framework incorporating: Linear combinations of categorical and continuous predictors, and interactions Response distributions in the exponential family (binomial, Poisson, and extensions) Any smooth, monotonic link function (e.g. logistic, exponential models) Flexible combinations of blocking factors (clustering; random eects) Applications in ecology, neurobiology, behaviour, epidemiology, real estate, . . . Ben Bolker GLMMs
  • 7. Denitions Statistics Computation Sociological Conclusions References Generalized linear mixed models GLMMs: a statistical modeling framework incorporating: Linear combinations of categorical and continuous predictors, and interactions Response distributions in the exponential family (binomial, Poisson, and extensions) Any smooth, monotonic link function (e.g. logistic, exponential models) Flexible combinations of blocking factors (clustering; random eects) Applications in ecology, neurobiology, behaviour, epidemiology, real estate, . . . Ben Bolker GLMMs
  • 8. Denitions Statistics Computation Sociological Conclusions References Technical denition Yi response ∼ conditional distribution Distr (g −1(ηi ) inverse link function , φ scale parameter ) η linear predictor = Xβ xed eects + Zb random eects b conditional modes ∼ MVN(0, Σ(θ) variance- covariance matrix ) Ben Bolker GLMMs
  • 9. Denitions Statistics Computation Sociological Conclusions References Outline 1 Denitions and context 2 Statistical challenges 3 Computational challenges 4 Sociological challenges 5 Conclusions Ben Bolker GLMMs
  • 10. Denitions Statistics Computation Sociological Conclusions References Estimation Maximum likelihood estimation L(Yi |θ, β) likelihood = · · · L(Yi |θ, β ) data|random eects × L(β |Σ(θ)) random eects dβ deterministic: precision vs. computational cost: penalized quasi-likelihood, Laplace approximation, adaptive Gauss-Hermite quadrature (Breslow, 2004) . . . Monte Carlo: frequentist and Bayesian (Booth and Hobert, 1999; Ponciano et al., 2009; Sung, 2007) Ben Bolker GLMMs
  • 11. Denitions Statistics Computation Sociological Conclusions References Estimation: example (McKeon et al., 2012) Log−odds of predation −6 −4 −2 0 2 Symbiont Crab vs. Shrimp Added symbiont q q q q q q q q q q q q q q q GLM (fixed) GLM (pooled) PQL Laplace AGQ Ben Bolker GLMMs
  • 12. Denitions Statistics Computation Sociological Conclusions References Inference Big problem. Inferential tools: either asymptotic or taken from classical linear models boundary solutions (Stram and Lee, 1994) the great p-value/degrees of freedom debate small numbers of clusters solutions: computational and/or Bayesian (parametric bootstrap, MCMC) True p value Inferredpvalue 0.02 0.04 0.06 0.08 0.02 0.06 Osm Cu H2S 0.02 0.06 0.02 0.04 0.06 0.08 Anoxia Ben Bolker GLMMs
  • 13. Denitions Statistics Computation Sociological Conclusions References Outline 1 Denitions and context 2 Statistical challenges 3 Computational challenges 4 Sociological challenges 5 Conclusions Ben Bolker GLMMs
  • 14. Denitions Statistics Computation Sociological Conclusions References Sparse matrix algorithms repeated decomposition of large, matrices (especially Z) ll-reducing permutation to improve sparsity pattern further improvements possible: better matrix representation, parallelization? Ben Bolker GLMMs
  • 15. Denitions Statistics Computation Sociological Conclusions References Bounded optimization Parameterize variance-covariance matrix Σ(θ) (Pinheiro and Bates, 1996) Positive denite or only semi-denite? Disadvantages of transforming to unconstrain (Disadvantages of boundary solutions) raw log 0 10 20 30 0 1 2 3 −3 −2 −1 0 deviance Ben Bolker GLMMs
  • 16. Denitions Statistics Computation Sociological Conclusions References Outline 1 Denitions and context 2 Statistical challenges 3 Computational challenges 4 Sociological challenges 5 Conclusions Ben Bolker GLMMs
  • 17. Denitions Statistics Computation Sociological Conclusions References Sociological issues The curse of neophilia Wide user base: As usual when software for complicated statistical inference procedures is broadly disseminated, there is potential for abuse and misinterpretation. (Breslow, 2004) What if there is no good answer? do no harm vs. better me than someone else Diagnostics and warning messages End users vs. downstream developers Ben Bolker GLMMs
  • 18. Denitions Statistics Computation Sociological Conclusions References Outline 1 Denitions and context 2 Statistical challenges 3 Computational challenges 4 Sociological challenges 5 Conclusions Ben Bolker GLMMs
  • 19. Denitions Statistics Computation Sociological Conclusions References Next steps Alternative platforms/languages Flexible correlation structures: spatial, temporal, phylogenetic . . . Improved MCMC methods? Simulation tests of inferential tools (sigh) Ben Bolker GLMMs
  • 20. Denitions Statistics Computation Sociological Conclusions References Is it science? Science is what we understand well enough to explain to a computer. Art is everything else we do. (Donald Knuth) 10 20 30 40 50 2006 2008 2010 2012 Date articlespermonth key glmm lme4 Ben Bolker GLMMs
  • 21. Denitions Statistics Computation Sociological Conclusions References Acknowledgments lme4: Doug Bates, Martin Mächler, Steve Walker Data: Adrian Stier (UBC/OSU), Sea McKeon (Smithsonian), David Julian (UF) NSERC (Discovery) SHARCnet Ben Bolker GLMMs
  • 22. Denitions Statistics Computation Sociological Conclusions References Booth, J.G. and Hobert, J.P., 1999. Journal of the Royal Statistical Society. Series B, 61(1):265285. doi:10.1111/1467-9868.00176. Breslow, N.E., 2004. In D.Y. Lin and P.J. Heagerty, editors, Proceedings of the second Seattle symposium in biostatistics: Analysis of correlated data, pages 122. Springer. ISBN 0387208623. McKeon, C.S., Stier, A., et al., 2012. Oecologia, 169(4):10951103. ISSN 0029-8549. doi:10.1007/s00442-012-2275-2. Pinheiro, J.C. and Bates, D.M., 1996. Statistics and Computing, 6(3):289296. doi:10.1007/BF00140873. Ponciano, J.M., Taper, M.L., et al., 2009. Ecology, 90(2):356362. ISSN 0012-9658. Stram, D.O. and Lee, J.W., 1994. Biometrics, 50(4):11711177. Sung, Y.J., 2007. The Annals of Statistics, 35(3):9901011. ISSN 0090-5364. doi:10.1214/009053606000001389. Ben Bolker GLMMs