Authors:Rodney Sparapani; Charles Spanbauer, Robert McCulloch Abstract: In this article, we introduce the BART R package which is an acronym for Bayesian additive regression trees. BART is a Bayesian nonparametric, machine learning, ensemble predictive modeling method for continuous, binary, categorical and time-to-event outcomes. Furthermore, BART is a tree-based, black-box method which fits the outcome to an arbitrary random function, f , of the covariates. The BART technique is relatively computationally efficient as compared to its competitors, but large sample sizes can be demanding. Therefore, the BART package includes efficient state-of-the-art implementations for continuous, binary, categorical and time-to-event outcomes that can take advantage of modern off-the-shelf hardware and software multi-threading technology. The BART package is written in C++ for both programmer and execution efficiency. The BART package takes advantage of multi-threading via forking as provided by the parallel package and OpenMP when available and supported by the platform. The ensemble of binary trees produced by a BART fit can be stored and re-used later via the R predict function. In addition to being an R package, the installed BART routines can be called directly from C++. The BART package provides the tools for your BART toolbox. PubDate: Thu, 14 Jan 2021 02:07:31 +000
Authors:Michael W. Robbins; Steven Davenport Abstract: The R package microsynth has been developed for implementation of the synthetic control methodology for comparative case studies involving micro- or meso-level data. The methodology implemented within microsynth is designed to assess the efficacy of a treatment or intervention within a well-defined geographic region that is itself a composite of several smaller regions (where data are available at the more granular level for comparison regions as well). The effect of the intervention on one or more time-varying outcomes is evaluated by determining a synthetic control region that resembles the treatment region across pre-intervention values of the outcome(s) and time-invariant covariates and that is a weighted composite of many untreated comparison regions. The microsynth procedure includes functionality that enables its user to (1) calculate weights for synthetic control, (2) tabulate results for statistical inferences, and (3) create time series plots of outcomes for treatment and synthetic control. In this article, microsynth is described in detail and its application is illustrated using data from a drug market intervention in Seattle, WA. PubDate: Thu, 14 Jan 2021 02:07:31 +000
Authors:Samuel L. Brilleman; Rory Wolfe, Margarita Moreno-Betancur, Michael J. Crowther Abstract: The simsurv R package allows users to simulate survival (i.e., time-to-event) data from standard parametric distributions (exponential, Weibull, and Gompertz), two-component mixture distributions, or a user-defined hazard function. Baseline covariates can be included under a proportional hazards assumption. Clustered event times, for example individuals within a family, are also easily accommodated. Time-dependent effects (i.e., nonproportional hazards) can be included by interacting covariates with linear time or a user-defined function of time. Under a user-defined hazard function, event times can be generated for a variety of complex models such as flexible (spline-based) baseline hazards, models with time-varying covariates, or joint longitudinal-survival models. PubDate: Thu, 14 Jan 2021 02:07:31 +000
Authors:Andreas Hill; Alexander Massey, Daniel Mandallaz Abstract: Forest inventories provide reliable evidence-based information to assess the state and development of forests over time. They typically consist of a random sample of plot locations in the forest that are assessed individually by field crews. Due to the high costs of these terrestrial campaigns, remote sensing information available in high quantity and low costs is frequently incorporated in the estimation process in order to reduce inventory costs or improve estimation precision. With respect to this objective, the application of multiphase forest inventory methods (e.g., double- and triple-sampling regression estimators) has proved to be efficient. While these methods have been successfully applied in practice, the availability of open-source software has been rare if not non-existent. The R package forestinventory provides a comprehensive set of global and small area regression estimators for multiphase forest inventories under simple and cluster sampling. The implemented methods have been demonstrated in various scientific studies ranging from small to large scale forest inventories, and can be used for post-stratification, regression and regression within strata. This article gives an extensive review of the mathematical theory of this family of design-based estimators, puts them into a common framework of forest inventory scenarios and demonstrates their application in the R environment. PubDate: Thu, 14 Jan 2021 02:07:31 +000
Open Access journal
