Efficient way to design and conduct psychological experiments for testing the performance of large language models. It simplifies the process of setting up experiments and data collection via language modelsâ API, facilitating a smooth workflow for researchers in the field of machine behaviour.

Multisite causal mediation analysis using the methods proposed by Qin and Hong (2017) <doi:10.3102/1076998617694879>, Qin, Hong, Deutsch, and Bein (2019) <doi:10.1111/rssa.12446>, and Qin, Deutsch, and Hong (2021) <doi:10.1002/pam.22268>. It enables causal mediation analysis in multisite trials, in which individuals are assigned to a treatment or a control group at each site. It allows for estimation and hypothesis testing for not only the population average but also the between-site variance of direct and indirect effects transmitted through one single mediator or two concurrent (conditionally independent) mediators. This strategy conveniently relaxes the assumption of no treatment-by-mediator interaction while greatly simplifying the outcome model specification without invoking strong distributional assumptions. This package also provides a function that can further incorporate a sample weight and a nonresponse weight for multisite causal mediation analysis in the presence of complex sample and survey designs and non-random nonresponse, to enhance both the internal validity and external validity. The package also provides a weighting-based balance checking function for assessing the remaining overt bias.

This package provides an extension to MadanText for creating and analyzing co-occurrence networks in Persian text data. This package mainly makes use of the PersianStemmer (Safshekan, R., et al. (2019). <https://CRAN.R-project.org/package=PersianStemmer>), udpipe (Wijffels, J., et al. (2023). <https://CRAN.R-project.org/package=udpipe>), and shiny (Chang, W., et al. (2023). <https://CRAN.R-project.org/package=shiny>) packages.

Family Planning programs and initiatives typically use nationally representative surveys to estimate key indicators of a countryâ s family planning progress. However, in recent years, routinely collected family planning services data (Service Statistics) have been used as a supplementary data source to bridge gaps in the surveys. The use of service statistics comes with the caveat that adjustments need to be made for missing private sector contributions to the contraceptive method supply chain. Evaluating the supply source of modern contraceptives often relies on Demographic Health Surveys (DHS), where many countries do not have recent data beyond 2015/16. Fortunately, in the absence of recent surveys we can rely on statistical model-based estimates and projections to fill the knowledge gap. We present a Bayesian, hierarchical, penalized-spline model with multivariate-normal spline coefficients, to account for across method correlations, to produce country-specific,annual estimates for the proportion of modern contraceptive methods coming from the public and private sectors. This package provides a quick and convenient way for users to access the DHS modern contraceptive supply share data at national and subnational administration levels, estimate, evaluate and plot annual estimates with uncertainty for a sample of low- and middle-income countries. Methods for the estimation of method supply shares at the national level are described in Comiskey, Alkema, Cahill (2022) <arXiv:2212.03844>.

Fit (by Maximum Likelihood or MCMC/Bayesian), simulate, and forecast various Markov-Switching GARCH models as described in Ardia et al. (2019) <doi:10.18637/jss.v091.i04>.

This package provides tools for high-dimensional peaks-over-threshold inference and simulation of Brown-Resnick and extremal Student spatial extremal processes. These include optimization routines based on censored likelihood and gradient scoring, and exact simulation algorithms for max-stable and multivariate Pareto distributions based on rejection sampling. Fast multivariate Gaussian and Student distribution functions using separation-of-variable algorithm with quasi Monte Carlo integration are also provided. Key references include de Fondeville and Davison (2018) <doi:10.1093/biomet/asy026>, Thibaud and Opitz (2015) <doi:10.1093/biomet/asv045>, Wadsworth and Tawn (2014) <doi:10.1093/biomet/ast042> and Genz and Bretz (2009) <doi:10.1007/978-3-642-01689-9>.

Correlation coefficients for multivariate data, namely the squared correlation coefficient and the RV coefficient (multivariate generalization of the squared Pearson correlation coefficient). References include Mardia K.V., Kent J.T. and Bibby J.M. (1979). "Multivariate Analysis". ISBN: 978-0124712522. London: Academic Press.

This will allow easier management of a CRAN-style repository on local networks (i.e. not on CRAN). This might be necessary where hosted packages contain intellectual property owned by a corporation.

Apply tests of multiple comparisons based on studentized midrange and range distributions. The tests are: Tukey Midrange ('TM test), Student-Newman-Keuls Midrange ('SNKM test), Means Grouping Midrange ('MGM test) and Means Grouping Range ('MGR test). The first two tests were published by Batista and Ferreira (2020) <doi:10.1590/1413-7054202044008020>. The last two were published by Batista and Ferreira (2023) <doi:10.28951/bjb.v41i4.640>.

Interface to the Google Maps APIs: (1) routing directions based on the Directions API, returned as sf objects, either as single feature per alternative route, or a single feature per segment per alternative route; (2) travel distance or time matrices based on the Distance Matrix API; (3) geocoded locations based on the Geocode API, returned as sf objects, either points or bounds; (4) map images using the Maps Static API, returned as stars objects.

This package provides a mixed collection of useful and semi-useful diverse statistical functions, some of which may even be referenced in The R Primer book. See Ekstrøm, C. T. (2016). The R Primer. 2nd edition. Chapman & Hall.

Mass measurement corrections and uncertainties using calibration data, as recommended by EURAMET's guideline No. 18 (2015) ISBN:978-3-942992-40-4 . The package provides classes, functions, and methods for storing information contained in calibration certificates and converting balance readings to both conventional mass and real mass. For the latter, the Magnitude of the Air Buoyancy Correction factor employs models (such as the CIMP-2007 formula revised by Picard, Davis, Gläser, and Fujii (2008) <doi:10.1088/0026-1394/45/2/004>) to estimate the local air density using measured environmental conditions.

Fit Maximum Entropy Optimality Theory models to data sets, generate the predictions made by such models for novel data, and compare the fit of different models using a variety of metrics. The package is described in Mayer, C., Tan, A., Zuraw, K. (in press) <https://sites.socsci.uci.edu/~cjmayer/papers/cmayer_et_al_maxent_ot_accepted.pdf>.

This package provides methods to estimate serial intervals and time-varying case reproduction numbers from infectious disease outbreak data. Serial intervals measure the time between symptom onset in linked transmission pairs, while case reproduction numbers quantify how many secondary cases each infected individual generates over time. These parameters are essential for understanding transmission dynamics, evaluating control measures, and informing public health responses. The package implements the maximum likelihood framework from Vink et al. (2014) <doi:10.1093/aje/kwu209> for serial interval estimation and the retrospective method from Wallinga & Lipsitch (2007) <doi:10.1098/rspb.2006.3754> for reproduction number estimation. Originally developed for scabies transmission analysis but applicable to other infectious diseases including influenza, COVID-19, and emerging pathogens. Designed for epidemiologists, public health researchers, and infectious disease modelers working with outbreak surveillance data.

This package provides a comprehensive range of facilities to perform umbrella reviews with stratification of the evidence in R. The package accomplishes this aim by building on three core functions that: (i) automatically perform all required calculations in an umbrella review (including but not limited to meta-analyses), (ii) stratify evidence according to various classification criteria, and (iii) generate a visual representation of the results. Note that if you are not familiar with R, the core features of this package are available from a web browser (<https://www.metaumbrella.org/>).

Fits multiple variable mixtures of various parametric proportional hazard models using the EM-Algorithm. Proportionality restrictions can be imposed on the latent groups and/or on the variables. Several survival distributions can be specified. Missing values and censored values are allowed. Independence is assumed over the single variables.

Analyzes production and dispersal of seeds dispersed from trees and recovered in seed traps. Motivated by long-term inventory plots where seed collections are used to infer seed production by each individual plant.

Estimators for multivariate symmetrical uncertainty based on the work of Gustavo Sosa et al. (2016) <arXiv:1709.08730>, total correlation, information gain and symmetrical uncertainty of categorical variables.

The goal of McMiso is to provide functions for isotonic regression when there are multiple independent variables. The functions solve the optimization problem using recursion and leverage parallel computing to improve speed, and are useful for situations with relatively large number of covariates. The estimation method follows the projective Bayes solution described in Cheung and Diaz (2023) <doi:10.1093/jrsssb/qkad014>.

Estimates average treatment effects using model average double robust (MA-DR) estimation. The MA-DR estimator is defined as weighted average of double robust estimators, where each double robust estimator corresponds to a specific choice of the outcome model and the propensity score model. The MA-DR estimator extend the desirable double robustness property by achieving consistency under the much weaker assumption that either the true propensity score model or the true outcome model be within a specified, possibly large, class of models.

The Macroeconomics-at-Risk (MaR) approach is based on a two-step semi-parametric estimation procedure that allows to forecast the full conditional distribution of an economic variable at a given horizon, as a function of a set of factors. These density forecasts are then be used to produce coherent forecasts for any downside risk measure, e.g., value-at-risk, expected shortfall, downside entropy. Initially introduced by Adrian et al. (2019) <doi:10.1257/aer.20161923> to reveal the vulnerability of economic growth to financial conditions, the MaR approach is currently extensively used by international financial institutions to provide Value-at-Risk (VaR) type forecasts for GDP growth (Growth-at-Risk) or inflation (Inflation-at-Risk). This package provides methods for estimating these models. Datasets for the US and the Eurozone are available to allow testing of the Adrian et al (2019) model. This package constitutes a useful toolbox (data and functions) for private practitioners, scholars as well as policymakers.

Analyses the stability and structural behaviour of export and import patterns across multiple countries using a Markov chain modelling framework. Constructs transition probability matrices to quantify changes in trade shares between successive periods, thereby capturing persistence, structural shifts, and inter-country interdependence in trade performance. By iteratively generating expected trade distributions over time, the approach facilitates assessment of stability, long-run equilibrium tendencies, and comparative dynamics in longitudinal trade data, providing a rigorous tool for empirical analysis of exportâ import behaviour. Methodological foundations follow standard Markov chain theory as described in Gagniuc (2017) <Doi:10.1002/9781119387596>.

Straightforward and detailed evaluation of machine learning models. MLeval can produce receiver operating characteristic (ROC) curves, precision-recall (PR) curves, calibration curves, and PR gain curves. MLeval accepts a data frame of class probabilities and ground truth labels, or, it can automatically interpret the Caret train function results from repeated cross validation, then select the best model and analyse the results. MLeval produces a range of evaluation metrics with confidence intervals.

This package provides two variants of multiple correspondence analysis (ca): multiple ca and ordered multiple ca via orthogonal polynomials of Emerson.