Skip to main content English


logistiX implements exact conditional logistic regression in R, including maximum conditional likelihood, median unbiased and Firth-corrected extimation methods, and twice-smaller-tail, probability and scores methods for hypothesis tests, with optional P-mid adjustment. For confidence interval estimation, various methods are available, such as exact, P-mid and integrated randomized variants, as well as the profile penalized completely conditional likelihood method discussed in Heinze and Puhr, 2010. The construction of the exact conditional permutational distributions is based on the Multivariate Shift Algorithm by Hirji et al, 1989. In contrast to other, Monte-Carlo or Markov-chain-Monte-Carlo approaches, logistiX is based on exact permutation distributions of the sufficient statistics.

Author(s): Georg Heinze and Tobias Ladner
Maintainer: Georg Heinze <>


Heinze, G., Puhr, R. (2010): "Bias-reduced and separation-proof conditional logistic regression with small or sparse data sets", Statistics in Medicine 29, 770 - 777 (doi:10.1002/sim.3794)
Hirji, KF., Mehta, CR. and Patel, NR. (1987): "Computing Distributions for Exact Logistic Regression." Journal of the American Statistical Association 82, 1110-1117


The package is available for download below:

Our programs are free of charge. However, before download, we would like you to supply your name and e-mail address here; we may then notify you if a new version is published:


logistiX 1.0, windows binary




logistiX, source package






Download: logistiX-Manual