Unmatched Monotone Regression

Unmatched regression refers to the regression setting where covariates and predictors are collected separately/independently and so are not paired together, as in the usual regression setting. Balabdaoui, Doss, and Durot (2021) study the unmatched regression setting where the univariate regression function is known to be monotone. This package implements methods for computing the estimator developed in Balabdaoui, Doss, and Durot (2021). The main method is an active-set-trust-region-based method.

Downscaling Species Occupancy

Uses species occupancy at coarse grain sizes to predict species occupancy at fine grain sizes. Ten models are provided to fit and extrapolate the occupancy-area relationship, as well as methods for preparing atlas data for modelling. See Marsh et. al. (2018) .

Partial Orders and Relations

Finds equivalence classes corresponding to a symmetric relation or undirected graph. Finds total order consistent with partial order or directed graph (so-called topological sort).

K-Means with Simultaneous Outlier Detection

An implementation of the 'k-means--' algorithm proposed by Chawla and Gionis, 2013 in their paper, "k-means-- : A unified approach to clustering and outlier detection. SIAM International Conference on Data Mining (SDM13)", and using 'ordering' described by Howe, 2013 in the thesis, Clustering and anomaly detection in tropical cyclones". Useful for creating (potentially) tighter clusters than standard k-means and simultaneously finding outliers inexpensively in multidimensional space.

Package for Reading Binary Files

Functions and analytics for GENEA-compatible accelerometer data into R objects. See topic 'GENEAread' for an introduction to the package. See < https://activinsights.com/technology/geneactiv/> for more details on the GENEActiv device.

Continuous Time SEM - 'OpenMx' Based Functions

Original 'ctsem' (continuous time structural equation modelling) functionality, based on the 'OpenMx' software, as described in Driver, Oud, Voelkle (2017) , with updated details in vignette. Combines stochastic differential equations representing latent processes with structural equation measurement models. These functions were split off from the main package of 'ctsem', as the main package uses the 'rstan' package as a backend now -- offering estimation options from max likelihood to Bayesian. There are nevertheless use cases for the wide format SEM style approach as offered here, particularly when there are no individual differences in observation timing and the number of individuals is large. For the main 'ctsem' package, see < https://cran.r-project.org/package=ctsem>.

Advanced 'tryCatch()' and 'try()' Functions

Advanced tryCatch() and try() functions for better error handling (logging, stack trace with source code references and support for post-mortem analysis via dump files).

Two Stage Hazard Rate Comparison

Two-stage procedure compares hazard rate functions, which may or may not cross each other.

k-Nearest Neighbor Join for Spatial Data

K-nearest neighbor search for projected and non-projected 'sf' spatial layers. Nearest neighbor search uses (1) C code from 'GeographicLib' for lon-lat point layers, (2) function knn() from package 'nabor' for projected point layers, or (3) function st_distance() from package 'sf' for line or polygon layers. The package also includes several other utility functions for spatial analysis.

Tools for Flexible Survival Analysis Using Machine Learning

Statistical tools for analyzing time-to-event data using machine learning. Implements survival stacking for conditional survival estimation, standardized survival function estimation for current status data, and methods for algorithm-agnostic variable importance. See Wolock CJ, Gilbert PB, Simon N, and Carone M (2024) .