R Packages


Popular R package that specializes on (univariate) time series imputation. It offers several different imputation algorithm implementations. Beyond the imputation algorithms the package also provides plotting and printing functions of time series missing data statistics.


R package for ridge regression with Automatic Selection of the Penalty Parameter. Initially developed by E. Cule, I was a regular package user at first. But I took over upkeep after it was dropped from CRAN, because it was missing a maintainer/did not pass the tests anymore. I fix bugs and perform small improvements on the package from time to time.


R package that provides a general framework for missing values imputation based on automated variable selection. The imputation is based on expectation maximization (EM) combined with machine learning (ML) algorithms. Lingbing F. wrote the initial version for his PhD thesis. Meanwhile, he is busy with different topics and I took over maintenance and tried to make some improvements to the package. Ideally, if time permits we plan to also provide more extensive updates for the package.


R package for detecting/classifying events in time-series data. It aims to combine multiple well-known R-packages like the forecast package to deliver an easily configurable tool for event detection. The package originates from research projects at TH Köln about anomaly detection in drinking water networks. I helped to develop the package and still occasionally contribute code.