Melanie Colón Posted July 6, 2017 Share Posted July 6, 2017 Applied Bayesian modelling for ecologists and epidemiologists (ABME03)Delivered by Dr. Matt Denwood and Prof. Jason Matthiopouloshttp://www.prstatistics.com/course/applied-bayesian-modelling-ecologists-epidemiologists-abme03/This 6 day course will run from 20th – 25th November 2017 at SCENE fieldstation, Loch Lomond national park, Scotland.This application-driven course will provide a founding in the basic theory& practice of Bayesian statistics, with a focus on MCMC modelling forecological & epidemiological problems.Starting from a refresher on probability & likelihood, the course will takestudents all the way to cutting-edge applications such as state-spacepopulation modelling & spatial point-process modelling. By the end of theweek, you should have a basic understanding of how common MCMC samplerswork and how to program them, and have practical experience with the BUGSlanguage for common ecological and epidemiological models. The experiencegained will be a sufficient foundation enabling you to understand currentpapers using Bayesian methods, carry out simple Bayesian analyses on yourown data and springboard into more elaborate applications such asdynamical, spatial and hierarchical modelling.Course content is as followsDay 1• Revision of likelihoods using full likelihood profiles and anintroduction to the theory of Bayesian statistics.o Probability and likelihoodo Conditional, joint and total probability, independence, Baye’s lawo Probability distributionso Uniform, Bernoulli, Binomial, Poisson, Gamma, Beta and Normaldistributions – their range, parameters and common usesoLikelihood andparameter estimation by maximum likelihoodo Numerical likelihood profiles and maximum likelihood• Introduction to Bayesian statisticso Relationship between prior, likelihood & posterior distributionso Summarising a posterior distribution; The philosophical differencesbetween frequentist & Bayesian statistics, & the practical implications oftheseo Applying Bayes’ theorem to discrete & continuous data for commondata types given different priorso Building a posterior profile for a given dataset, & compare theeffect of different priors for the same dataDay 2• An introduction to the workings of mcmc, and the potential dangersof mcmc inference. Participants will program their own (basic) mcmcsampler to illustrate the concepts and fully understand the strengths andweaknesses of the general approach. The day will end with an introductionto the bugs language.o Introduction to MCMC.o The curse of dimensionality & the advantages of MCMC sampling todetermine a posterior distribution.o Monte Carlo integration, standard error, & summarising samples fromposterior distributions in R .o Writing a Metropolis algorithm & generating a posteriordistribution for a simple problem using MCMC.o Markov chains, autocorrelation & convergence.o Definition of a Markov chain.o Autocorrelation, effective sample size and Monte Carlo error.o The concept of a stationary distribution and burning.o Requirement for convergence diagnostics, and common statistics forassessing convergence.o Adapting an existing Metropolis algorithm to use two chains, &assessing the effect of the sampling distribution on the autocorrelation.o Introduction to BUGS & running simple models in JAGS.o Introduction to the BUGS language & how a BUGS model is translatedto an MCMC sampler during compilation.o The difference between deterministic & stochastic nodes, & thecontribution of priors & the likelihood.o Running, extending & interpreting the output of simple JAGS modelsfrom within R using the runjags interface.Day 3• This day will focus on the common models for which jags/bugs wouldbe used in practice, with examples given for different types of modelcode. All aspects of writing, running, assessing and interpreting thesemodels will be extensively discussed so that participants are able andconfident to run similar models on their own. There will be a particularlyheavy focus on practical sessions during this day. The day will finishwith a discussion of how to assess the fit of mcmc models using thedeviance information criterion (dic) and other methods.o Using JAGS for common problems in biology.o Understanding and generating code for basic generalised linearmixed models in JAGS.o Syntax for quadratic terms and interaction terms in JAGS.o Essential fitting tips and model selection.o The need for minimal cross-correlation and independence betweenparameters and how to design a model with these properties.o The practical methods and implications of minimizing Monte Carloerror and autocorrelation, including thinning.o Interpreting the DIC for nested models, and understanding thelimitations of how this is calculated.o Other methods of model selection and where these might be moreuseful than DIC.o Most commonly used methods Rationale and use for fixed threshold,ABGD, K/theta, PTP, GMYC with computer practicals.o Other methods, Haplowebs, bGMYC, etc. with computer practicalsDay 4• Day 4 will focus on the flexibility of mcmc, and precautionsrequired for using mcmc to model commonly encountered datasets. Anintroduction to conjugate priors and the potential benefits of exploitinggibbs sampling will be given. More complex types of models such ashierarchical models, latent class models, mixture models and state spacemodels will be introduced and discussed. The practical sessions willfollow on from day 3.o General guidance for model specification.o The flexibility of the BUGS language and MCMC methods.o The difference between informative and diffuse priors.o Conjugate priors and how they can be used.o Gibbs sampling.o State space models.o Hierarchical and state space models.o Latent class and mixture models.o Conceptual application to animal movement.o Hands-on application to population biology.o Conceptual application to epidemiologyDay 5• Day 5 will give some additional practical guidance for the use ofBayesian methods in practice, and finish with a brief overview of moreadvanced Bayesian tools such as inla and stan.o Additional Bayesian methods.o Understand the usefulness of conjugate priors for robust analysisof proportions (Binomial and Multinomial data).o Be aware of some methods of prior elicitation.o Advanced Bayesian tools.o Strengths and weaknesses of Integrated Nested Laplace Approximation(INLA) compared to BUGS.o Strengths and weaknesses of Stan compared to BUGSDay 6• Round table discussions and problem solving with final Q and Around table discussion and problem solving with final Q and A.o The final day will consist of round table discussions, the classwill be split in to smaller groups to discuss set topics/problems. Thiswill include participants own data where possible. After an early lunchthere will be a general question and answer time until approx. 2pm as awhole group before transport to Balloch train station.There will be a 15 minute morning coffee break, an hour for lunch, and a15minute afternoon coffee break. We keep the timing of these flexibledepending how the course advances. Breakfast is from 08:00-08:45 and dinneris at 18:00 each day.Please email any inquiries to email@example.com or visit ourwebsite www.prstatistics.comPlease feel free to distribute this material anywhere you feel is suitable-----------------------------------------------------------------------------------------------------------------PR stats other courses1. META-ANALYSIS IN ECOLOGY, EVOLUTION AND ENVIRONMENTAL SCIENCES#METR0124th – 28th July, Scotland, Prof. Julia Koricheva, Prof. Elena Kulinskayahttp://www.prstatistics.com/course/meta-analysis-in-ecology-evolution-and-environmental-sciences-metr01/2. SPATIAL ANALYSIS OF ECOLOGICAL DATA USING R #SPAE7th – 12th August 2017, Scotland, Prof. Jason Matthiopoulos, Dr. JamesGrecianhttp://www.prstatistics.com/course/spatial-analysis-ecological-data-using-r-spae05/3. ECOLOGICAL NICHE MODELLING USING R #ENMR16th – 20th October 2017, Scotland, Dr. Neftali Sillerohttp://www.prstatistics.com/course/ecological-niche-modelling-using-r-enmr01/4. GENETIC DATA ANALYSIS AND EXPLORATION USING R #GDAR23rd – 27th October, Wales, Dr. Thibaut Jombart, Zhian Kavarhttp://www.prstatistics.com/course/genetic-data-analysis-exploration-using-r-gdar03/5. STRUCTURAL EQUATION MODELLING FOR ECOLOGISTS AND EVOLUTIONARYBIOLOGISTS USING R #SEMR23rd – 27th October, Wales, Prof Jarrett Byrnes, Dr. Jon Lefcheckhttp://www.prstatistics.com/course/structural-equation-modelling-for-ecologists-and-evolutionary-biologists-semr01/6. LANDSCAPE (POPULATION) GENETIC DATA ANALYSIS USING R #LNDG6th – 10th November, Wales, Prof. Rodney Dyerhttp://www.prstatistics.com/course/landscape-genetic-data-analysis-using-r-lndg02/7. APPLIED BAYESIAN MODELLING FOR ECOLOGISTS AND EPIDEMIOLOGISTS #ABME20th - 25th November 2017, Scotland, Prof. Jason Matthiopoulos, Dr. MattDenwoodhttp://www.prstatistics.com/course/applied-bayesian-modelling-ecologists-epidemiologists-abme03/8. ADVANCING IN STATISTICAL MODELLING USING R #ADVR11th – 15th December 2017, Wales, Dr. Luc Bussiere, Dr. Tom Houslay, Dr.Ane Timenes Laugen,http://www.prstatistics.com/course/advancing-statistical-modelling-using-r-advr07/9. INTRODUCTION TO BAYESIAN HIERARCHICAL MODELLING #IBHM29th Jan – 2nd Feb 2018, Scotland, Dr. Andrew Parnellhttp://www.prstatistics.com/course/introduction-to-bayesian-hierarchical-modelling-using-r-ibhm02/10. PHYLOGENETIC DATA ANALYSIS USING R (TBC) #PHYL28th Jan – Feb 2nd Dr. Emmanuel Paradis – Date and location to be confirmedhttps://www.prstatistics.com/course/introduction-to-phylogenetic-analysis-with-r-phyg-phyl02/11. ANIMAL MOVEMENT ECOLOGY (February 2018) #ANME19th – 23rd February 2018, Wales, Dr Luca Borger, Dr. John Fieberg12. GEOMETRIC MORPHOMETRICS USING R #GMMR5th – 9th June 2017, Scotland, Prof. Dean Adams, Prof. Michael Collyer, Dr.Antigoni Kaliontzopoulouhttp://www.prstatistics.com/course/geometric-morphometrics-using-r-gmmr01/13. FUNCTIONAL ECOLOGY FROM ORGANISM TO ECOSYSTEM: THEORY ANDCOMPUTATION #FEER5th – 9th March 2018, Scotland, Dr. Francesco de Bello, Dr. LarsGötzenberger, Dr. Carlos Carmonahttp://www.prstatistics.com/course/functional-ecology-from-organism-to-ecosystem-theory-and-computation-feer01/14. MODEL BASE MULTIVARIATE ANALYSIS OF ABUNDANCE DATA USING R #MBMV08th – 12th July 2018, Prof David Warton15. ADVANCES IN MULTIVARIATE ANALYSIS OF SPATIAL ECOLOGICAL DATA USINGR #MVSPProf. Pierre Legendre, Dr. Olivier Gauthier - Date and location to beconfirmed16. STABLE ISOTOPE MIXING MODELS USING SIAR, SIBER AND MIXSIAR #SIMMDr. Andrew Parnell, Dr. Andrew Jackson – Date and location to be confirmed17. NETWORK ANAYLSIS FOR ECOLOGISTS USING R #NTWADr. Marco Scotti - Date and location to be confirmed18. MULTIVARIATE ANALYSIS OF SPATIAL ECOLOGICAL DATA #MASEProf. Subhash Lele, Dr. Peter Solymos - Date and location to be confirmed19. TIME SERIES MODELS FOR ECOLOGISTS USING R (JUNE 2017 #TSMEDr. Andrew Parnell - Date and location to be confirmed-----------------------------------------------------------------------------------------------------------------PR informatics other courses1. BIOINFORMATICS FOR GENETICISTS AND BIOLOGISTS #BIGB3rd – 7th July 2017, Scotland, Dr. Nic Blouin, Dr. Ian Misnerhttp://www.prinformatics.com/course/bioinformatics-for-geneticists-and-biologists-bigb02/2. INTRODUCTION TO BIOINFORMATICS USING LINUX #IBUL16th – 20th October, Scotland, Dr. Martin Joneshttp://www.prstatistics.com/course/introduction-to-bioinformatics-using-linux-ibul02/3. INTRODUCTION TO PYTHON FOR BIOLOGISTS #IPYB27th Nov – 1st Dec, Wales, Dr. Martin Joneshttp://www.prinformatics.com/course/introduction-to-python-for-biologists-ipyb04/4. INTRODUCTION REMOTE SENSING AND GIS APPLICATIONS FOR ECOLOGISTS#IRMS27th Nov – 1st Dec, Wales, Dr Duccio Rocchini, Dr. Luca Delucchihttp://www.prstatistics.com/course/introduction-to-remote-sensing-and-gis-for-ecological-applications-irms01/5. DATA VISUALISATION AND MANIPULATION USING PYTHON #DVMP11th – 15th December 2017, Wales, Dr. Martin Joneshttp://www.prinformatics.com/course/data-visualisation-and-manipulation-using-python-dvmp01/6. EUKARYOTIC METABARCODING23rd – 27th July 2018, Scotland, Dr. Owen Wangensteenhttp://www.prinformatics.com/course/eukaryotic-metabarcoding-eukb01/7. CODING, DATA MANAGEMENT AND SHINY APPLICATIONS USING RSTUDIO FOREVOLUTIONARY BIOLOGISTS AND ECOLOGISTS #CDSRDr. Aline Quadros--Oliver Hooker PhD.PR statistics2017 publications -Ecosystem size predicts eco-morphological variability in post-glacialdiversification. Ecology and Evolution. In press.The physiological costs of prey switching reinforce foragingspecialization. Journal of animal ecology.prstatistics.comfacebook.com/prstatistics/twitter.com/PRstatisticsgroups.google.com/d/forum/pr-statistics-post-course-forumprstatistics.com/organiser/oliver-hooker/3/1, 128 Brunswick StreetGlasgowG1 1TF+44 (0) 7966500340 Link to comment Share on other sites More sharing options...
This topic is now archived and is closed to further replies.