# Trustees of Columbia University

#### 21 packages on CRAN

Running and comparing meta-analyses of data with hierarchical Bayesian models in Stan, including convenience functions for formatting data, plotting and pooling measures specific to meta-analysis.

Contains several Bayesian models for data analysis of psychological tests. A user friendly interface for these models should enable students and researchers to perform professional level Bayesian data analysis without advanced knowledge in programming and Bayesian statistics.

Natural history museums and herbaria collectively hold hundreds of millions of zoological, botanical, and paleontological specimens. These collections serve as the foundation for understanding the distribution of life on Earth and the basis for addressing loss of biodiversity, emerging diseases, and other pressing global problems as well as important question in ecology and evolution. One of the short comings of these kind of data is that the lack of evidence of the presence of a species in a certain region does not mean the species is truly absent there. Likewise, specimens are often misidentified, and therefore the report of a species in a locality is not always evidence that a viable population occurs there. The goal of this project is to develop a method which could be used to estimate the probability of presence of a species in a certain study region based on certain sampling effort and presence reports.

Hierarchical continuous time state space modelling, for linear and nonlinear systems measured by continuous variables, with limited support for binary data. The subject specific dynamic system is modelled as a stochastic differential equation (SDE), measurement models are typically multivariate normal factor models. Using the original ctsem formulation based on OpenMx, described in the JSS paper "Continuous Time Structural Equation Modeling with R Package ctsem", with updated version as CRAN vignette <https://cran.r-project.org/web/packages/ctsem/vignettes/ctsem.pdf> , linear mixed effects SDE's estimated via maximum likelihood and optimization are possible. Using the Stan based formulation, described in <https://github.com/cdriveraus/ctsem/raw/master/vignettes/hierarchicalmanual.pdf> , nonlinearity (state dependent parameters) and random effects on all parameters are possible, using either optimization (with optional importance sampling) or Stan's Hamiltonian Monte Carlo sampling. Priors may be used. For the conceptual overview of the hierarchical Bayesian linear SDE approach, see <https://www.researchgate.net/publication/324093594_Hierarchical_Bayesian_Continuous_Time_Dynamic_Modeling>. Exogenous inputs may also be included, for an overview of such possibilities see <https://www.researchgate.net/publication/328221807_Understanding_the_Time_Course_of_Interventions_with_Continuous_Time_Dynamic_Models> . Stan based functions are not available on 32 bit Windows systems at present.

Statistical methods involving PK measures are provided, in the dose allocation process during a Phase I clinical trials. These methods, proposed by Ursino et al, (2017) <doi:10.1002/bimj.201600084>, enter pharmacokinetics (PK) in the dose finding designs in different ways, including covariates models, dependent variable or hierarchical models. This package provides functions to generate data from several scenarios and functions to run simulations which their objective is to determine the maximum tolerated dose (MTD).

An implementation of Bayesian hierarchical models for faecal egg count data to assess anthelmintic efficacy. Bayesian inference is done via MCMC sampling using 'Stan' <https://mc-stan.org/>.

Implements Bayesian spatial and spatiotemporal models that optionally allow for extreme spatial deviations through time. 'glmmfields' uses a predictive process approach with random fields implemented through a multivariate-t distribution instead of the usual multivariate normal. Sampling is conducted with 'Stan'. References: Anderson and Ward (2019) <doi:10.1002/ecy.2403>.

Offers item-response theory (IRT) ideal-point estimation for binary, ordinal, counts and continuous responses with time-varying and missing-data inference. Full and approximate Bayesian sampling with 'Stan' (<https://mc-stan.org/>).

Performs Bayesian meta-analysis and model-based meta-analysis using 'Stan'. Includes binomial-normal hierarchical models and option to use weakly informative priors for the heterogeneity parameter and the treatment effect parameter which are described in Guenhan, Roever, and Friede (2018) <arXiv:1809.04407>.

Bayesian logistic regression model with optional EXchangeability-NonEXchangeability parameter modelling for flexible borrowing from historical or concurrent data-sources. The safety model can guide dose-escalation decisions for adaptive oncology Phase I dose-escalation trials which involve an arbitrary number of drugs. Please refer to Neuenschwander et al. (2008) <doi:10.1002/sim.3230> and Neuenschwander et al. (2016) <doi:10.1080/19466315.2016.1174149> for details on the methodology.

Provides convenience functions and pre-programmed Stan models related to the paired comparison factor model. Its purpose is to make fitting paired comparison data using Stan easy.

Tool-set to support Bayesian evidence synthesis. This includes meta-analysis, (robust) prior derivation from historical data, operating characteristics and analysis (1 and 2 sample cases). Please refer to Neuenschwander et al. (2010) <doi:10.1177/1740774509356002> and Schmidli et al. (2014) <doi:10.1111/biom.12242> for details on the methodology.

An implementation of a number of Global Trend models for time series forecasting that are Bayesian generalizations and extensions of some Exponential Smoothing models. The main differences/additions include 1) nonlinear global trend, 2) Student-t error distribution, and 3) a function for the error size, so heteroscedasticity. The methods are particularly useful for short time series. When tested on the well-known M3 dataset, they are able to outperform all classical time series algorithms. The models are fitted with MCMC using the 'rstan' package.

Estimates different multiple discrete-continuous extreme value (MDCEV) demand model specifications with observed and unobserved individual heterogeneity (Bhat (2008) <doi:10.1016/j.trb.2007.06.002>). Fixed parameter, latent class, and random parameter models can be estimated. These models are estimated using maximum likelihood or Bayesian estimation techniques and are implemented in 'Stan', which is a C++ package for performing full Bayesian inference (see Stan Development Team (2018) <http://mc-stan.org>). The 'rmdcev' package also includes functions for demand simulation (Pinjari and Bhat (2011) <https://repositories.lib.utexas.edu/handle/2152/23880>) and welfare simulation (Lloyd-Smith (2018) <doi:10.1016/j.jocm.2017.12.002>).

User-facing R functions are provided to parse, compile, test, estimate, and analyze Stan models by accessing the header-only Stan library provided by the 'StanHeaders' package. The Stan project develops a probabilistic programming language that implements full Bayesian statistical inference via Markov Chain Monte Carlo, rough Bayesian inference via 'variational' approximation, and (optionally penalized) maximum likelihood estimation via optimization. In all three cases, automatic differentiation is used to quickly and accurately evaluate gradients without burdening the user with the need to derive the partial derivatives.

Estimates previously compiled regression models using the 'rstan' package, which provides the R interface to the Stan C++ library for Bayesian estimation. Users specify models via the customary R syntax with a formula and data.frame plus some additional arguments for priors.

Perform sigmoidal Emax model fit using 'Stan' in a formula notation, without writing 'Stan' model code.

Provides various tools for developers of R packages interfacing with 'Stan' <https://mc-stan.org>, including functions to set up the required package structure, S3 generics and default methods to unify function naming across 'Stan'-based R packages, and vignettes with recommendations for developers.

The C++ header files of the Stan project are provided by this package, but it contains no R code or function documentation. There is a shared object containing part of the 'CVODES' library, but it is not accessible from R. 'StanHeaders' is only useful for developers who want to utilize the 'LinkingTo' directive of their package's DESCRIPTION file to build on the Stan library without incurring unnecessary dependencies. The Stan project develops a probabilistic programming language that implements full or approximate Bayesian statistical inference via Markov Chain Monte Carlo or 'variational' methods and implements (optionally penalized) maximum likelihood estimation via optimization. The Stan library includes an advanced automatic differentiation scheme, 'templated' statistical and linear algebra functions that can handle the automatically 'differentiable' scalar types (and doubles, 'ints', etc.), and a parser for the Stan language. The 'rstan' package provides user-facing R functions to parse, compile, test, estimate, and analyze Stan models.

Fit Thurstonian Item Response Theory (IRT) models in R. This package supports fitting Thurstonian IRT models and its extensions using 'Stan', 'lavaan', or 'Mplus' for the model estimation. Functionality for extracting results and simulating data is provided as well. References: Brown & Maydeu-Olivares (2011) <doi:10.1177/0013164410375112>; B<c3><bc>rkner et al. (2019) <doi:10.1177/0013164419832063>.

A collection of clinical trial designs and methods, implemented in 'rstan' and R, including: the Continual Reassessment Method by O'Quigley et al. (1990) <doi:10.2307/2531628>; EffTox by Thall & Cook (2004) <doi:10.1111/j.0006-341X.2004.00218.x>; and the Augmented Binary method by Wason & Seaman (2013) <doi:10.1002/sim.5867>; and more. We provide functions to aid model-fitting and analysis. The 'rstan' implementations may also serve as a cookbook to anyone looking to extend or embellish these models. We hope that this package encourages the use of Bayesian methods in clinical trials. There is a preponderance of early phase trial designs because this is where Bayesian methods are used most. If there is a method you would like implemented, please get in touch.