R-packages

A considerable amount of software grew out of my research. Most of this code is made available as packages for the freely available software R and can be downloaded from CRAN. The packages were first uploaded to CRAN in the years indicated.

[9] Schuhmacher, D., Rufibach, K., Dümbgen L. (2011). logconcens: Maximum likelihood estimation of a log-concave density based on censored data.

[8] Rufibach, K., Balabdaoui, F., Jankowski, H., Weyermann, K. (2011). logcondiscr: Estimate a Log-Concave Probability Mass function from Discrete i.i.d. Observations. Paper

[7] Rufibach, K. (2010). selectMeta: Estimation of weight functions in meta analysis. Paper

[6] Rufibach, K. (2009). OrdFacReg: Least squares, logistic, and Cox-regression with ordered predictors. Paper

[5] Balabdaoui, F., Rufibach, K., Santambrogio, F. (2009). OrdMonReg: Compute least squares estimates of one bounded or two ordered antitonic regression curves. Paper

[4] Rufibach, K. (2008). reporttools: Generate LaTeX tables of descriptive statistics. Paper

[3] Rufibach, K., Walther, G. (2007). modehunt: Multiscale analysis about a density. Paper

[2] Rufibach, K., Müller, S. (2006). smoothtail: Smooth Estimation of GPD Shape Parameter. Paper

[1] Rufibach, K., Dümbgen, L. (2006). logcondens: Estimate a Log-Concave Probability Density from i.i.d. Observations. Paper 1 Paper 2 Paper 3 Paper 4

While working at the Division of Biostatistics at the University of Zurich I maintained another R package, biostatUZH, which is not publicly available. This package collected all functions that were developed at the department at that time.

Contributions to R-packages

The methodology introduced in Rufibach, K. (2012), A smooth ROC curve estimator based on log-concave density estimates is also available in the function smooth() in the R package pROC .

Further software

Below you find some R code that has not (yet) made it into a proper R package.

ROC curve estimator based on kernel estimates of the constituent distributions

Confidence intervals in group sequential trials for a binomial parameter

design: ojo3.com