A Logging Utility Focus on Clinical Trial Programming Workflows

A utility to facilitate the logging and review of R programs in clinical trial programming workflows.

Parsing Semi-Structured Log Files into Tabular Format

Convert semi-structured log files (such as 'Apache' access.log files) into a tabular format (data.frame) using a standard template system.

Penalized Log-Density Estimation Using Legendre Polynomials

We present a penalized log-density estimation method using Legendre polynomials with lasso penalty to adjust estimate's smoothness. Re-expressing the logarithm of the density estimator via a linear combination of Legendre polynomials, we can estimate parameters by maximizing the penalized log-likelihood function. Besides, we proposed an implementation strategy that builds on the coordinate decent algorithm, together with the Bayesian information criterion (BIC).

Relative Risk Regression Using the Log-Binomial Model

Methods for fitting log-link GLMs and GAMs to binomial data, including EM-type algorithms with more stable convergence properties than standard methods.

Fit Log-Ratio Lasso Regression for Compositional Data

Log-ratio Lasso regression for continuous, binary, and survival outcomes with (longitudinal) compositional features. See Fei and others (2024) .

Odd Log-Logistic Generalized Gamma Probability Distribution

Density, distribution function, quantile function and random generation for the Odd Log-Logistic Generalized Gamma proposed in Prataviera, F. et al (2017) .

Fits the Bayesian Piecewise Linear Log-Hazard Model

Contains posterior samplers for the Bayesian piecewise linear log-hazard and piecewise exponential hazard models, including Cox models. Posterior mean restricted survival times are also computed for non-Cox an Cox models with only treatment indicators. The ApproxMean() function can be used to estimate restricted posterior mean survival times given a vector of patient covariates in the Cox model. Functions included to return the posterior mean hazard and survival functions for the piecewise exponential and piecewise linear log-hazard models. Chapple, AG, Peak, T, Hemal, A (2020). Under Revision.

Log-Concave Distribution Estimation with Interval-Censored Data

We consider the non-parametric maximum likelihood estimation of the underlying distribution function, assuming log-concavity, based on mixed-case interval-censored data. The algorithm implemented is base on Chi Wing Chu, Hok Kan Ling and Chaoyu Yuan (2024, ).

Utilities from 'Seminar fuer Statistik' ETH Zurich

Useful utilities ['goodies'] from Seminar fuer Statistik ETH Zurich, some of which were ported from S-plus in the 1990s. For graphics, have pretty (Log-scale) axes eaxis(), an enhanced Tukey-Anscombe plot, combining histogram and boxplot, 2d-residual plots, a 'tachoPlot()', pretty arrows, etc. For robustness, have a robust F test and robust range(). For system support, notably on Linux, provides 'Sys.*()' functions with more access to system and CPU information. Finally, miscellaneous utilities such as simple efficient prime numbers, integer codes, Duplicated(), toLatex.numeric() and is.whole().

Ordinal Outcomes: Generalized Linear Models with the Log Link

An implementation of the Log Cumulative Probability Model (LCPM) and Proportional Probability Model (PPM) for which the Maximum Likelihood Estimates are determined using constrained optimization. This implementation accounts for the implicit constraints on the parameter space. Other features such as standard errors, z tests and p-values use standard methods adapted from the results based on constrained optimization.