CR 64: 187-199 Supplementary Material

Almaraz P
Bordeaux wine quality and climate fluctuations during the last century: changing temperatures and changing industry
CR 64:187-199 | Full text in pdf format


Supplement 1 (pdf)

Supplemennt 2 (RStan code)
This code, commented when appropriate, fits the time-varying coefficients and constant regression models through Bayesian HMC to evaluate the effects of growing season temperature on Bordeaux wine quality ratings from 1920 to 2009. The RStan version used was Version 2.5.0, packaged: 2014-10-22 14:19:22 UTC, GitRev: e52c66f42e81, running in R version 3.1.2 (2014-10-31) -- "Pumpkin Helmet" © 2014 The R Foundation for Statistical Computing, Platform: x86_64-w64-mingw32/x64 (64-bit).

CAUTIONARY NOTE: The code will reproduce exactly the results presented in the accompanying paper, and priors are set to the RStan default with random diffuse initial values. Note, however, that this model is heavily parameterized, so it is suggested that users modifying this code for their own analyses set stringent priors and initial values so that the posterior converges to a stationary distribution. As well as with MCMC, HMC can be dangerous!

This work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc/4.0/ or send a letter to Creative Commons, 444 Castro Street, Suite 900, Mountain View, California, 94041, USA. Please, cite the accompanying paper if using this code