July 30, 2016

Installation

example("stan_model", package = "rstan", run.dontrun = TRUE)
  • Also, verify that packageVersion("rstanarm") is 2.11.1; otherwise execute
install.packages("rstanarm", repos = "https://cloud.r-project.org", dependencies = TRUE)
install.packages("rstanarm", repos = "https://cloud.r-project.org", type = "source")

Outline

  1. Introduction
  2. Hamiltonian Markov Chain Monte Carlo
  3. An rstanarm example
  4. Writing Stan programs
  5. Hierarchcial models
  6. Case study with optimal book pricing

Obligatory Disclosure

  • Ben is an employee of Columbia University, which has received several research grants to develop Stan
  • Ben is also a cofounder of Stan Group (http://stan.fit), which provides support, consulting, etc. for businesses using Stan
  • According to Columbia University policy, any such employee who has any equity stake in, a title (such as officer or director) with, or is expected to earn at least \(\$5,000.00\) per year from a private company is required to disclose these facts in presentations
  • Eric is also a cofounder of Stan Group but not a Columbia employee and hence is not implicated by the above

Introduction

Who Is Using Stan?

  • Stan is used in academia, business, and government
  • Downloads
    • rstan:
    • rstanarm:
    • brms:
    • Lots of PyStan downloads
    • ~ 10,000+ manual downloads with each new release
  • Over 1,000 mailing list registrations
  • Stan is used for fitting climate models, clinical drug trials, genomics and cancer biology, population dynamics, psycholinguistics, social networks, finance and econometrics, professional sports, publishing, recommender systems, educational testing, and many more.

Stan in Pharmacometrics