The next Cologne R user group meeting is scheduled for this Friday, 12 December 2014.
We have an exciting agenda with two talks on Julia and Dynamic Linear Models:
Introduction to Julia for R Users
Hans Werner Borchers
Julia is a high-performance dynamic programming language for scientific computing, with a syntax that is familiar to users of other technical computing environments (Matlab, Python, R, etc.). It provides a sophisticated compiler, high performance with numerical accuracy, and extensive mathematical function libraries.
Some of the highlights of Julia are an implementation of automated differentiation, an optimisation modelling language, also integrating some of the optimisation solvers available from the COIN-OR project, and user-contributed packages for time series, statistics and machine learning, or operations research.
Dynamic Linear Models and Kalman Filtering
One of the problems most commonly presented to everybody working in statistics is forecasting time series. The textbook answer is to fit an ARMA model to the data and to use the model for prediction. This approach works well for long and stationary time series. However, often the actual time series one is given to analyse are more complicated. They are ridiculously short and clearly non-stationary. Dynamic Linear Models (DLM) and Kalman Filtering go one step beyond ARMA models and may be applied to these more complicated data. I will give a brief introduction into their mathematical background and will talk about my experience using them in practice.
Drinks and Networking
The event will be followed by drinks and schnitzel at the Lux.