Partial Least Squares Path Modeling (PLS-PM)

Partial Least Squares Path Modeling (PLS-PM), Tenenhaus, Esposito Vinzi, Chatelin, Lauro (2005) , analysis for both metric and non-metric data, as well as REBUS analysis, Esposito Vinzi, Trinchera, Squillacciotti, and Tenenhaus (2008) .

Translate ICD-9 into Injury Severity Score

Calculate the injury severity score (ISS) based on the dictionary in 'ICDPIC' from < https://ideas.repec.org/c/boc/bocode/s457028.html>. The original code was written in 'STATA 11'. The original 'STATA' code was written by David Clark, Turner Osler and David Hahn. I implement the same logic for easier access. Ref: David E. Clark & Turner M. Osler & David R. Hahn, 2009. "ICDPIC: Stata module to provide methods for translating International Classification of Diseases (Ninth Revision) diagnosis codes into standard injury categories and/or scores," Statistical Software Components S457028, Boston College Department of Economics, revised 29 Oct 2010.

Practical 'R' Packaging in 'Docker'

Streamline the creation of 'Docker' images with 'R' packages and dependencies embedded. The 'pracpac' package provides a 'usethis'-like interface to creating Dockerfiles with dependencies managed by 'renv'. The 'pracpac' functionality is described in Nagraj and Turner (2023) .

'eXtra' / 'eXperimental' Functionality for Robust Statistics

Robustness -- 'eXperimental', 'eXtraneous', or 'eXtraordinary' Functionality for Robust Statistics. Hence methods which are not well established, often related to methods in package 'robustbase'. Amazingly, 'BACON()', originally by Billor, Hadi, and Velleman (2000) has become established in places. The "barrow wheel" `rbwheel()` is from Stahel and Mächler (2009) .

Hidden Markov Models with Discrete Non-Parametric Observation Distributions

Fits hidden Markov models with discrete non-parametric observation distributions to data sets. The observations may be univariate or bivariate. Simulates data from such models. Finds most probable underlying hidden states, the most probable sequences of such states, and the log likelihood of a collection of observations given the parameters of the model. Auxiliary predictors are accommodated in the univariate setting.

Vegetated Filter Strip and Erosion Model

Empirical models for runoff, erosion, and phosphorus loss across a vegetated filter strip, given slope, soils, climate, and vegetation (Gall et al., 2018) . It also includes functions for deriving climate parameters from measured daily weather data, and for simulating rainfall. Models implemented include MUSLE (Williams, 1975) and APLE (Vadas et al., 2009 ).

Optimal Pricing of Assets with Fixed Expiry Date

Calculates the optimal price of assets (such as airline flight seats, hotel room bookings) whose value becomes zero after a fixed ``expiry date''. Assumes potential customers arrive (possibly in groups) according to a known inhomogeneous Poisson process. Also assumes a known time-varying elasticity of demand (price sensitivity) function. Uses elementary techniques based on ordinary differential equations. Uses the package deSolve to effect the solution of these differential equations.

Discretised Beta Distribution

Tools for working with a new versatile discrete distribution, the db ("discretised Beta") distribution. This package provides density (probability), distribution, inverse distribution (quantile) and random data generation functions for the db family. It provides functions to effect conveniently maximum likelihood estimation of parameters, and a variety of useful plotting functions. It provides goodness of fit tests and functions to calculate the Fisher information, different estimates of the hessian of the log likelihood and Monte Carlo estimation of the covariance matrix of the maximum likelihood parameter estimates. In addition it provides analogous tools for working with the beta-binomial distribution which has been proposed as a competitor to the db distribution.

The hse Distribution

Deprecated.

Safe Anytime-Valid Inference

Functions to design and apply tests that are anytime valid. The functions can be used to design hypothesis tests in the prospective/randomised control trial setting or in the observational/retrospective setting. The resulting tests remain valid under both optional stopping and optional continuation. The current version includes safe t-tests and safe tests of two proportions. For details on the theory of safe tests, see Grunwald, de Heide and Koolen (2019) "Safe Testing" , for details on safe logrank tests see ter Schure, Perez-Ortiz, Ly and Grunwald (2020) "The Safe Logrank Test: Error Control under Continuous Monitoring with Unlimited Horizon" and Turner, Ly and Grunwald (2021) "Safe Tests and Always-Valid Confidence Intervals for contingency tables and beyond" for details on safe contingency table tests.