Next TRUG meeting: 16 November

Our next meeting will take place on 16 November at 12 o’clock in the Cubicus building, room C124. Elze Ufkes will give a presentation on the analysis of twitter data in R.

The slides of the last meeting can be found here: 
https://twenterug.files.wordpress.com/2014/11/sukaesi.ppt

February meeting

Our February meeting will take place on 25 February (next week Wednesday) at 12 o’clock in the Cubicus building, room C124. Sukaesi Marianti will give a presentation on the estimation of growth models in R.

The slides of the December meeting can be found here: https://twenterug.files.wordpress.com/2014/11/trug_dec_2014_pipeline.pdf

Time & location of the next meeting

Due to the low responses, we decided to change the location of the next meeting (so you don’t have to bicycle to far-away Boekelo anymore).

The meeting will now take place on 15 December (next Monday) at 12 o’clock in the Cubicus building, room C232a.

The February-meeting has been postponed to 26 February (time, place + topic to be announced).

We hope to see you then!

Next TRUG meetings!

I am very happy to finally (!) pronounce the next two TRUG meetings!

Next meeting, Stéphanie van den Berg will give a presentation on a pipeline for analysing data on twins, using the R library knitr. The pipeline automatically reads in the data, runs the analysis and creates a LateX file with the results of the analysis. The LateX file is then automatically converted into a pdf file.

Depending on how many of you are able to come, the meeting will take place on December 15th (monday) or December 18th (thursday). Please indicate your preference:

We will inform you by e-mail about the exact date and location as soon as there is a clear preference for one of the dates. As usual, the meeting will take place at Stephanie’s little farm in Boekelo (time to be announced).

The meeting after that will take place on February 12th (thursday). Presenter will be Sukaesi Marianti (topic to be announced).

There is of course still a lot of time left to make up your mind, but if you already know that you can (or cannot) attend, please let us know:

The dplyr package

In the June ’14 meeting of the Twente R User group, Martin Schmettow gave a presentation on the R package ‘dplyr’. Code of this package runs fast, can transparently deal with remote data and produces readable code. Furthermore, it interfaces well with the plyr and ggplot package. You can find the slides of the presentation here: Dplyr package.

Next meeting: The dplyr package

At the next meeting, Wednesday 25 2014, Martin Schmettow will give a presentation on the R library dplyr.  The dplyr package provides useful tools for efficiently manipulating datasets in R. For those who are familiar with the package plyr, dplyr is the ‘next iteration’ of plyr. It focuses on data frames and is faster and easier to use than plyr.

We are meeting at Stephanie’s little  farm in Boekelo at 17.30. A group of TRUG members is going by bicycle to Boekelo. In case you want to join us, we are meeting at the entrance of the Cubicus building at 17.00 o’clock.

 

Object oriented programming in R

In the January ’14 meeting of the Twente R User group, Janina Torbecke & Inga Schwabe gave an introduction into object oriented programming in R. Although object oriented programming may be more straight forward in other programming languages (e.g. Python, Java, C++), it can be useful in R to enable the use of generic functions (e.g. for your own library), to program efficiently (e.g. elimination of redundant code) or just to produce neat code.

The code that was used to explain the idea of object oriented programming is part of a battleship game made in R. You can find the slides of the presentation here: Object oriented programming in R and the R code here: Battleship game in R.

P.S.: I posted this blog post directly from R, using the simple markdown language and the RWordPress library. To do this, I used the following code:

## Install Rwordpress library
if (!require("RWordPress")) install.packages("RWordPress", repos = "http://www.omegahat.org/R", 
    type = "source")

## Load packages & log in on wordpress
library(knitr)
library(RWordPress)
library(XML)

# Upload post to blog
options(WordPressLogin = c(ingaschwabe = "*****"), WordPressURL = "https://twenterug.wordpress.com/xmlrpc.php")
knit2wp("OOP_in_R.Rmd", title = "Object oriented programming in R", publish = TRUE)

If you want to do try this on your own blog, these are helpful links: http://fredhasselman.com/?p=303 and http://yihui.name/knitr/demo/wordpress/.

Interactive R learning

For those who are still learning the basics of the R programming language, the following website might be interesting:

http://www.datamind.org/

Another thing that might be interesting is the recently released R-library Swirl. The swirl R package is designed to simultaneously teach users statistics and the R programming language. In a typical swirl session, the user is required to load a package from the R console and chose from a menu of options the course he would like to take. Then he works through 10-15 minutes interactive modules, each covering a particular topic.

To install it, this is all you have to do in R:

#Install libraries
install.packages(“devtools”)
library(“devtools”)
install_github(repo=”swirl”, username=”ncarchedi”)
library(“swirl”)

#Call swirl()
swirl()

Note however that the package is yet released and constantly fixed and updated. It is therefore recommended to update the version at least one ca month so you have full access to the latest features.

This is the official website of the package: http://swirlstats.com
You can find a blog post on the release of the new package on Simply Statistics:
http://simplystatistics.org/2013/09/27/announcing-statistics-with-interactive-r-learning-software-environment

Monte carlo simulations in R

After a short summer break, the third meeting oft he TRUG took place on October 7th.

Henk Broekhuizen presented how R can be used for Monte Carlo simulations. Henk introduced the problem of combining probability distributions, then introduced the main ideas behind Monte Carlo simulations and finished with some outcomes from his own work in probabilistic MCDA models. In this kind of decision analysis, model outcomes are a complex function of the inputs. When these inputs are probability distributions, calculating the outcomes analytically becomes hard and sometimes impossible. Monte Carlo simulations are a useful and straightforward approach to approximate and visualize these model outcomes.  A pdf file of the presentation can be downloaded here: Third_TRUG_meeting

Resampling methods in R

The second meeting of the TRUG took place on July 11th.

Inga Schwabe gave an introduction into the world of resampling methods. Resampling methods can be a good alternative when classical statistical methods that are largely based on idealized assumptions (e.g. normal distribution) cannot be used for statistical inference. This was shown by means of a simple example: The empirical p value was calculated for the difference between the scores of a treatment and a control group by using a resampling method called ‘Permutation’. A pdf file of the presentation can be downloaded here: Second_TRUG_meeting