NIMBLE: A new way to do MCMC (and more) from BUGS code in R

Interesante … escribir BUGS pero sin utilizar BUGS…


Write statistical models in the BUGS language from R

NIMBLE adopts and extends BUGS as a modeling language and lets you program with the models you create.

Other packages that use the BUGS language are only for Markov chain Monte Carlo (MCMC). With NIMBLE, you can turn BUGS code into model objects and use them for whatever algorithm you want. That includes algorithms provided with NIMBLE and algorithms you write using nimbleFunctions. NIMBLE extends BUGS by allowing multiple parameterizations for distributions, user-written functions and distributions, and more.

Categories: Curriculum Tags:
Martes, 5 de julio de 2016 Sin comentarios

Introducing Microsoft R Open

Microsoft poco a poco se va introduciendo en el mundo del R, primero compr√≥ Revolutions-Analytics; y ahora ya ofrecve un R server… pues lo √ļltimo ha sido que RStudio tambien se puede conectar a este server y trabajar contra el.

Introducing Microsoft R Open: Replay and slides

We had a fantastic turnout to last week’s webinar, Introduction to Microsoft R Open. If you missed it, you can watch the replay below. In the talk, I gives some background on the R language and its applications, describe the performance and reproducibility benefits of Microsoft R Open, and give a demonstration of the basics of the R language along with a more in-depth demo of producing a beautiful weather data chart with R.

Categories: Curriculum Tags:
Domingo, 7 de febrero de 2016 Sin comentarios

A gentle introduction to parallel computing in R

Una buena introducción.

Categories: Curriculum Tags:
Miércoles, 20 de enero de 2016 Sin comentarios

Happy collaboration with Rmd to docx

Os dejo un enlace interesante: This article is reposted from with the kind permission of Richard Layton.


Categories: R & RStudio Tags:
Jueves, 23 de julio de 2015 Sin comentarios

Paquetes para manipular Datos en R

Computerworld’s list of R packages for data wrangling

Computerworld’s Sharon Machlis published today a very useful list of R packages that every R user should know. The list covers packages for data import, data wrangling, data visualization and package development, but for beginning R users the biggest challenge is usually just dealing with data. To that end, I thought it was worth listing the package for data access and manipulation, which I thoroughly endorse:

  • Data import/access:¬†readr¬†(text data files),¬†rio¬†(many binary data file formats),¬†readxl (Excel spreadsheets),¬†googlesheets (Google Sheets), RMySQL(MySQL databases),¬†quantmod (economic and financial data sources);
  • Data manipulation: dplyr (general data frame processing); data.table (aggregation and filtering); tidyr (tidying messy data into row/col format);¬†sqldf (SQL queries on data frames), zoo (time series data wrangling)

Check out Sharon’s complete list below for details on these and many other useful R packages.

Categories: R & RStudio Tags:
Viernes, 15 de mayo de 2015 Sin comentarios

Xavier Barber y el Big Data en Programa CIO, 10 de marzo de 2015

Xavier Barber y el Big Data en Programa CIO, 10 de marzo de 2015



100315 Programa CIO

Dirigido por Sergi Escrivá. Dedicado a la actualidad del Instituto Centro de Investigación Operativa (CIO) de la Universidad Miguel Hernández de Elche.

En el programa de hoy hemos entrevistado a Xavi Barber, investigador del CIO y licenciado en Ciencias y Técnicas Estadísiticas por la Universidad Miguel Hernández de Elche y Doctorado en Estadística e Investigación. Debido al auge de Internet y las nuevas tecnologías,  hoy en día resulta imprescindible gestionar grandes cantidades de datos. Para ello nació el término inglés Big Data. A ese concepto está dedicado el programa de hoy.


Categories: Curriculum Tags:
Miércoles, 11 de marzo de 2015 Sin comentarios

R Markdown Tutorial by RStudio and DataCamp

Interesante Videotutorial para empezar a trabajar con R y Markdown:

In collaboration with Garrett Grolemund, RStudio’s teaching specialist, DataCamp has developed a new interactive course to facilitate reproducible reporting of your R analyses. R Markdown enables you to generate reports straight from your R code, documenting your works as an HTML, pdf or Microsoft document. This course is part of DataCamp’s R training path, but can also be taken as a separate course.

Categories: R & RStudio Tags:
Martes, 3 de marzo de 2015 Sin comentarios

Los m√°s descargado de R en 2013/2014

Categories: Curriculum Tags:
Martes, 17 de febrero de 2015 Sin comentarios

Probable Points and Credible Intervals

A continuaci√≥n os enlazo dos “entradas de blog” muy muy interesantes:

Se trata de una introducción al la Teoría de Decisión desde la perspectiva  Bayesiana:


Categories: Statistical Modelling Tags:
Jueves, 8 de enero de 2015 Sin comentarios

14 razones por la que R es mejor que Excel(c)

14 Reasons Why R is better than Excel

This article was first published on Revolutions

The Fantasy Football Analytics blog shares these 14 reasons why R is better than Excel for data analysis:

  1. More powerful data manipulation capabilities
  2. Easier automation
  3. Faster computation
  4. It reads any type of data
  5. Easier project organization
  6. It supports larger data sets
  7. Reproducibility (important for detecting errors)
  8. Easier to find and fix errors
  9. It’s free
  10. It’s open source
  11. Advanced Statistics capabilities
  12. State-of-the-art graphics
  13. It runs on many platforms
  14. Anyone can contribute packages to improve its functionality

The two most important in my mind are #2 (automation) and #7 (reproducibility), reasons that apply to any GUI-driven tool. The ability to use code to repeat your analyses and reproduce the results consistently cannot be overstated.

For more detailed background behind each of these reasons, and four situations where it’s best to use Excel, check out the complete blog blost linked below.

Fantasy Football Analytics: Why R is Better Than Excel for Fantasy Football (and most other) Data Analysis

Categories: Divulgación Tags:
S√°bado, 11 de octubre de 2014 Sin comentarios