Learn Bayesian Data Analysis and Stan with Stan developer Jonah Gabry

Lander Analytics

Learn Bayesian Data Analysis (BDA) and Markov chain Monte Carlo (MCMC) computation using Stan with Stan developer <A HREF="https://jgabry.github.io/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">Jonah Gabry</A>.
This three-day workshop will be taught by <A HREF="https://jgabry.github.io/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">Jonah Gabry</A>. Jonah is a Stan developer based at Columbia University and the developer of <A HREF="https://jgabry.github.io/software-and-papers/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">many R packages</A> for applied Bayesian data analysis (rstan, rstanarm, rstantools, bayesplot, shinystan, loo). Jonah will be joined by fellow Stan developer Rob Trangucci, and other members of the Stan Development Team will make some guest appearances at various times throughout the course.
The course consists of three main themes:  Bayesian inference and computation; the Stan modeling language; applied statistics/Bayesian data analysis in practice. There will be some lectures to cover important concepts, but the course will also be heavily interactive, with much of the time dedicated to hands on examples. We will be interfacing with Stan from R, but users of Python and other languages/platforms can still benefit from the course as all of the code we write in the Stan language (and all of the modeling techniques and concepts covered in the course) can be used with any of the <A HREF="http://mc-stan.org/users/interfaces/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">Stan interfaces</A>. 
Participants will receive a copy of Andrew Gelman's landmark book <A HREF="http://www.stat.columbia.edu/~gelman/book/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">Bayesian Data Analysis</A>. Proceeds from the class support further development of <A HREF="http://mc-stan.org/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">Stan</A> and the <A HREF="http://www.nyhackr.org" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">New York Open Statistical Programming Meetup</A>.
Before class everyone should install <A HREF="http://www.r-project.org/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">R</A>, <A HREF="http://www.rstudio.com/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">RStudio</A> and <A HREF="https://github.com/stan-dev/rstan/wiki/RStan-Getting-Started" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">RStan</A> on their computers. If problems occur please join the <A HREF="http://discourse.mc-stan.org/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">stan-users</A> group and post any questions. It is important that all participants get Stan running and bring their laptops to the course.
Example topics and course structure is below. Actual coverage will be determined during the class based on the participants.
<H3>Section 1: Bayesian Inference in Theory and Practice</H3>
This section covers (or reviews, depending on the audience) the most essential concepts that form the foundations of Bayesian inference. The focus is on the necessary background required to successfully apply Bayesian statistics to real world problems.
<UL>
<LI>What is Bayesian inference and how does it differ from other forms of statistical inference?</LI>
<UL>
<LI>Advantages and disadvantages compared to frequentist inference and approximate forms of Bayesian inference</LI>
<LI>Generative models</LI>
<LI>The role of prior distributions in practice </LI>
<LI>Important properties of posterior distributions </LI>
</UL>
<LI>The Bayesian data analysis workflow</LI>
<UL>
<LI>Iterative model building, checking, and refinement </LI>
</UL>
<LI>Bayesian computation with Markov chain Monte Carlo</LI>
</UL>
<H3>Section 2: Intro to Stan</H3>
This section introduces the <A HREF="http://mc-stan.org/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">Stan</A> modeling language, <A HREF="https://cran.r-project.org/package=rstan" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">RStan</A>, the interface for fitting Stan models via R, and the rest of the Stan ecosystem (e.g., the many supporting R packages).  
<UL>
<LI>What is Stan and why is it an important tool for Bayesian data analysis? </LI>
<LI>Programming statistical models in the Stan language</LI>
<UL>
<LI>Understanding the structure of a Stan program</LI>
<LI>Key similarities and differences between the Stan language and other common programming languages</LI>
</UL>
<LI>Using the Stan interfaces to fit models</LI>
<UL>
<LI>Introduction to RStan, the R interface to Stan</LI>
<LI>Estimating models in Stan using data from an R session</LI>
<LI>Working with the fitted model objects returned by RStan </LI>
<LI>Brief intro to the Stan Development Team’s packages for diagnostics and visualization (<A HREF="http://mc-stan.org/bayesplot/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">bayesplot</A>, <A HREF="http://mc-stan.org/shinystan/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">shinystan</A>). More on these packages also in later sections.</LI>
</UL>
</UL>
<H3>Section 3: Linear and Generalized Linear Models in Stan</H3>
This section covers how to program the most commonly used regression models in Stan and fit them using the RStan interface. In subsequent sections we will add hierarchical structure to these models.
<UL>
<LI>Review of regression and generalized linear models (GLMs) from a Bayesian perspective </LI>
<LI>Programming and fitting GLMs in Stan </LI>
<UL>
<LI>Models for continuous data, binary data, count data</LI>
<LI>Examples will be drawn from various domains including A/B testing, political polling, clinical trials, sports and more</LI>
</UL>
<LI>How to think about specifying prior distributions for parameters in GLMs</LI>
<UL>
<LI>Weakly informative defaults</LI>
<LI>When are non-informative priors appropriate?</LI>
<LI>Translating prior knowledge into mathematical form</LI>
</UL>
</UL>
<H3>Section 4: Model Checking and Model Comparison</H3>
This section covers methods and tools for checking the fit of a model to data and comparing (or combining) multiple competing models.
<UL>
<LI>Understanding the role of the posterior predictive distribution for model checking</LI>
<LI>Graphical and numerical posterior predictive checking using the <A HREF="http://mc-stan.org/bayesplot/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">bayesplot</A> and <A HREF="http://mc-stan.org/shinystan/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">shinystan</A> R packages:</LI>
<UL>
<LI>How to use visualizations of the posterior predictive distribution to identify important features of the data not captured by a model</LI>
<LI>Using posterior predictive checks to motivate improvements to the A/B testing model from Section 3</LI>
</UL>
<LI>Comparing multiple models on estimated predictive performance</LI>
<UL>
<LI>When are techniques like cross-validation appropriate? </LI>
<LI>The importance of predictive power and explanatory power and then frequent tension between them</LI>
<LI>Introduction to the <A HREF="http://mc-stan.org/loo/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">loo</A> R package for model comparison and model averaging</LI>
</UL>
</UL>
<H3>Section 5: Hierarchical/Multilevel Models (Part 1)</H3>
In this section we focus on more advanced models that incorporate hierarchical structures unique to the particular application. These models are more difficult computationally and require paying more attention to diagnostics that motivate changes to the models.
<UL>
<LI>Review of hierarchical models from a Bayesian perspective</LI>
<UL>
<LI>Bias/variance tradeoff</LI>
<LI>Partial pooling, shrinkage, borrowing strength, regularization</LI>
<LI>Hyperpriors and hyperparameters </LI>
</UL>
<LI>Implementing hierarchical models in Stan</LI>
<UL>
<LI>Adding hierarchical structure to the GLMs from Section 3</LI>
<LI>Coding tips for balancing ease of programming, code clarity, and computational efficiency</LI>
</UL>
<LI>Diagnosing and fixing computational problems when fitting hierarchical models</LI>
<UL>
<LI>Visual and numerical Markov Chain Monte Carlo diagnostics </LI>
<LI>Sampler tuning parameters</LI>
<LI>Reparameterization</LI>
</UL>
</UL>
<H3>Section 6: Hierarchical/Multilevel Models (Part 2)</H3>
In this section we continue with the topic of hierarchical models and introduce techniques for  decision making using inferences from the models.
<UL>
<LI>Intro to more advanced hierarchical modeling techniques </LI>
<UL>
<LI>Temporal variation </LI>
<LI>Spatial correlation structures</LI>
<LI>Splines and Gaussian processes </LI>
</UL>
<LI>Forecasting and out-of-sample prediction with hierarchical models</LI>
<UL>
<LI>Out-of-sample prediction using the generated quantities block of a Stan program</LI>
<LI>Decision analysis (e.g., setting prices to maximize expected revenue, cost/benefit analysis in healthcare) </LI>
</UL>
</UL>
<H3>Section 7: Wrapping Up</H3>
<UL>
<LI>Review essential concepts from previous sections</LI>
<LI>Time for discussing additional topics of interest to participants</LI>
<LI>Various tips and tricks for becoming an advanced Stan user</LI>
<LI>Q&A session with other Stan developers</LI>
</UL>
<H2>For more information please <A HREF="https://www.landeranalytics.com/contact" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">contact us</A>.</H2>

eBay NYC

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

Learn Bayesian Data Analysis and Stan with Stan developer Jonah Gabry

More events from Lander Analytics

Discover more events from Lander Analytics, from Science & Tech to other experiences you might love.

Still looking for the right event?

Explore all events in New York and filter by date, category, and more to find the perfect fit.

Learn Bayesian Data Analysis and Stan with Stan developer Jonah Gabry

More events from Lander Analytics

Discover more events from Lander Analytics, from Science & Tech to other experiences you might love.

You might also like...

Browse more events with different dates, prices, and formats to find your next great experience.

Still looking for the right event?

Explore all events in New York and filter by date, category, and more to find the perfect fit.