Robust Testing in GLMs (flipscores)
Provides two robust tests for testing in GLMs, by sign-flipping score contributions. The tests are often robust against overdispersion, heteroscedasticity and, in some cases, ignored nuisance variables. See Hemerik and Goeman (2017) <doi:10.1007/s11749-017-0571-1>.

Plot Population Demographic History (POPdemog)
Plot demographic graphs for single/multiple populations from coalescent simulation program input. Currently, this package can support the ‘ms’, ‘msHot’, ‘MaCS’, ‘msprime’, ‘SCRM’, and ‘Cosi2’ simulation programs. It does not check the simulation program input for correctness, but assumes the simulation program input has been validated by the simulation program. More features will be added to this package in the future, please check the ‘GitHub’ page for the latest updates: <https://…/POPdemog>.

Synthetic Population Generator (humanleague)
Generates high-entropy integer synthetic populations from marginal and (optionally) seed data using quasirandom sampling, in arbitrary dimensionality (Smith, Lovelace and Birkin (2017) <doi:10.18564/jasss.3550>). The package also provides an implementation of the Iterative Proportional Fitting (IPF) algorithm (Zaloznik (2011) <doi:10.13140/2.1.2480.9923>).

Proportional Hazards Mixed-Effects Model (PHMM) (phmm)
Fits proportional hazards model incorporating random effects using an EM algorithm using Markov Chain Monte Carlo at E-step. Vaida and Xu (2000) <doi:10.1002/1097-0258(20001230)19:24%3C3309::AID-SIM825%3E3.0.CO;2-9>.

Finding the Number of Significant Principal Components (PCDimension)
Implements methods to automate the Auer-Gervini graphical Bayesian approach for determining the number of significant principal components. Automation uses clustering, change points, or simple statistical models to distinguish ‘long’ from ‘short’ steps in a graph showing the posterior number of components as a function of a prior parameter.

High-Dimensional Variable Selection with Presence-Only Data (PUlasso)
Efficient algorithm for solving PU (Positive and Unlabelled) problem in low or high dimensional setting with lasso or group lasso penalty. The algorithm uses Maximization-Minorization and (block) coordinate descent. Sparse calculation and parallel computing via ‘OpenMP’ are supported for the computational speed-up. See Hyebin Song, Garvesh Raskutti (2017) <arXiv:1711.08129>.