CONCOR for Structural- And Regular-Equivalence Blockmodeling

The four functions svdcp() ('cp' for column partitioned), svdbip() or svdbip2() ('bip' for bipartitioned), and svdbips() ('s' for a simultaneous optimization of a set of 'r' solutions), correspond to a singular value decomposition (SVD) by blocks notion, by supposing each block depending on relative subspaces, rather than on two whole spaces as usual SVD does. The other functions, based on this notion, are relative to two column partitioned data matrices x and y defining two sets of subsets x_i and y_j of variables and amount to estimate a link between x_i and y_j for the pair (x_i, y_j) relatively to the links associated to all the other pairs. These methods were first presented in: Lafosse R. & Hanafi M.,(1997) < https://eudml.org/doc/106424> and Hanafi M. & Lafosse, R. (2001) < https://eudml.org/doc/106494>.

Bayesian Analysis of the Network Autocorrelation Model

The network autocorrelation model (NAM) can be used for studying the degree of social influence regarding an outcome variable based on one or more known networks. The degree of social influence is quantified via the network autocorrelation parameters. In case of a single network, the Bayesian methods of Dittrich, Leenders, and Mulder (2017) and Dittrich, Leenders, and Mulder (2019) are implemented using a normal, flat, or independence Jeffreys prior for the network autocorrelation. In the case of multiple networks, the Bayesian methods of Dittrich, Leenders, and Mulder (2020) are implemented using a multivariate normal prior for the network autocorrelation parameters. Flat priors are implemented for estimating the coefficients. For Bayesian testing of equality and order-constrained hypotheses, the default Bayes factor of Gu, Mulder, and Hoijtink, (2018) is used with the posterior mean and posterior covariance matrix of the NAM parameters based on flat priors as input.

R Wrappers for EXPOKIT; Other Matrix Functions

Wraps some of the matrix exponentiation utilities from EXPOKIT (< http://www.maths.uq.edu.au/expokit/>), a FORTRAN library that is widely recommended for matrix exponentiation (Sidje RB, 1998. "Expokit: A Software Package for Computing Matrix Exponentials." ACM Trans. Math. Softw. 24(1): 130-156). EXPOKIT includes functions for exponentiating both small, dense matrices, and large, sparse matrices (in sparse matrices, most of the cells have value 0). Rapid matrix exponentiation is useful in phylogenetics when we have a large number of states (as we do when we are inferring the history of transitions between the possible geographic ranges of a species), but is probably useful in other ways as well. NOTE: In case FORTRAN checks temporarily get rexpokit archived on CRAN, see archived binaries at GitHub in: nmatzke/Matzke_R_binaries (binaries install without compilation of source code).

Joint Mean and Covariance Estimation for Matrix-Variate Data

Jointly estimates two-group means and covariances for matrix-variate data and calculates test statistics. This package implements the algorithms defined in Hornstein, Fan, Shedden, and Zhou (2018) .

Dimension Reduction, Regression and Discrimination for Chemometrics

Data exploration and prediction with focus on high dimensional data and chemometrics. The package was initially designed about partial least squares regression and discrimination models and variants, in particular locally weighted PLS models (LWPLS). Then, it has been expanded to many other methods for analyzing high dimensional data. The name 'rchemo' comes from the fact that the package is orientated to chemometrics, but most of the provided methods are fully generic to other domains. Functions such as transform(), predict(), coef() and summary() are available. Tuning the predictive models is facilitated by generic functions gridscore() (validation dataset) and gridcv() (cross-validation). Faster versions are also available for models based on latent variables (LVs) (gridscorelv() and gridcvlv()) and ridge regularization (gridscorelb() and gridcvlb()).

A Byte-Pair-Encoding (BPE) Tokenizer for OpenAI's Large Language Models

A thin wrapper around the tiktoken-rs crate, allowing to encode text into Byte-Pair-Encoding (BPE) tokens and decode tokens back to text. This is useful to understand how Large Language Models (LLMs) perceive text.

Bayesian Model to Estimate Population Trends from Counts Series

Infers the trends of one or several animal populations over time from series of counts. It does so by accounting for count precision (provided or inferred based on expert knowledge, e.g. guesstimates), smoothing the population rate of increase over time, and accounting for the maximum demographic potential of species. Inference is carried out in a Bayesian framework. This work is part of the FRB-CESAB working group AfroBioDrivers < https://www.fondationbiodiversite.fr/en/the-frb-in-action/programs-and-projects/le-cesab/afrobiodrivers/>.

Goodness-of-Fit Tests for Capture-Recapture Models

Performs goodness-of-fit tests for capture-recapture models as described by Gimenez et al. (2018) . Also contains several functions to process capture-recapture data.

Computes Statistics for Relational Event History Data

Computes a variety of statistics for relational event models. Relational event models enable researchers to investigate both exogenous and endogenous factors influencing the evolution of a time-ordered sequence of events. These models are categorized into tie-oriented models (Butts, C., 2008, ), where the probability of a dyad interacting next is modeled in a single step, and actor-oriented models (Stadtfeld, C., & Block, P., 2017, ), which first model the probability of a sender initiating an interaction and subsequently the probability of the sender's choice of receiver. The package is designed to compute a variety of statistics that summarize exogenous and endogenous influences on the event stream for both types of models.

Fast Network Modularity and Roles Computation by Simulated Annealing (Rgraph C Library Wrapper for R)

Provides functions to compute the modularity and modularity-related roles in networks. It is a wrapper around the rgraph library (Guimera & Amaral, 2005, ).