Network-Based Regularization for Generalized Linear Models (regnet)
Network-based regularization has achieved success in variable selections for high-dimensional biological data, due to its ability to incorporate the correlations among genomic features.This package provides procedures for fitting network-based regularization, minimax concave penalty (MCP) and lasso penalty for generalized linear models. This first version, regent0.1.0, focuses on binary outcomes. Functions for continuous, survival outcomes and other regularization methods will be included in the forthcoming upgraded version.

R Optimization Infrastructure: ‘MIPLIB’ 2010 Benchmark Instances (ROI.models.miplib)
The mixed integer programming library ‘MIPLIB’ (see <http://…/> ) is commonly used to compare the performance of mixed integer optimization solvers. This package provides functions to access ‘MIPLIB’ from the ‘R’ Optimization Infrastructure (‘ROI’). More information about ‘MIPLIB’ can be found in the paper by Koch et al. available at <http://…/28>. The ‘’ file illustrates how to use this package.

The Wally Calibration Plot for Risk Prediction Models (wally)
A prediction model is calibrated if, roughly, for any percentage x we can expect that x subjects out of 100 experience the event among all subjects that have a predicted risk of x%. A calibration plot provides a simple, yet useful, way of assessing the calibration assumption. The Wally plot consists of a sequence of usual calibration plots. Among the plots contained within the sequence, one is the actual calibration plot which has been obtained from the data and the others are obtained from similar simulated data under the calibration assumption. It provides the investigator with a direct visual understanding of the shape and sampling variability that are common under the calibration assumption. The original calibration plot from the data is included randomly among the simulated calibration plots, similarly to a police lineup. If the original calibration plot is not easily identified then the calibration assumption is not contradicted by the data. The method handles the common situations in which the data contain censored observations and occurrences of competing events.

Permutations and Mallows Distributions (PerMallows)
Includes functions to work with the Mallows and Generalized Mallows Models. The considered distances are Kendall’s-tau, Cayley, Hamming and Ulam and it includes functions for making inference, sampling and learning such distributions, some of which are novel in the literature. As a by-product, PerMallows also includes operations for permutations, paying special attention to those related with the Kendall’s-tau, Cayley, Ulam and Hamming distances. It is also possible to generate random permutations at a given distance, or with a given number of inversions, or cycles, or fixed points or even with a given length on LIS (longest increasing subsequence).

Some Latent Variable Models (LAM)
Contains some procedures for latent variable modelling with a particular focus on multilevel data. The LAM package contains mean and covariance structure modelling for multivariate normally distributed data (‘mlnormal’), a general Metropolis-Hastings algorithm (‘amh’) and penalized maximum likelihood estimation (‘pmle’).