Low-Rank Interaction Contingency Tables (lori)
Estimation and visualization of low-rank interaction contingency tables. Low-rank interaction is a two-fold extension of the log-bilinear model. First, instead of a fixed rank constraint, the log-likelihood is penalized by the nuclear norm of the interaction matrix. Second, available row and column covariates can be incorporated in the model. The main function can be applied to contingency tables with missing values. G. Robin, J. Josse, E. Moulines, S. Sardy (2017) <arXiv:1703.02296>.

A ‘Shiny’ Application for Inspecting Structural Topic Models (stminsights)
This app enables interactive validation, interpretation and visualization of structural topic models from the ‘stm’ package by Roberts and others (2014) <doi:10.1111/ajps.12103>. It also includes helper functions for model diagnostics and extracting data from effect estimates.

Discrete Bayesian Additive Regression Trees Sampler (dbarts)
Fits Bayesian additive regression trees (BART) while allowing the updating of predictors or response so that BART can be incorporated as a conditional model in a Gibbs/MH sampler. Also serves as a drop-in replacement for package ‘BayesTree’.

Rosenbaum and Rubin Sensitivity (rnr)
Apply sensitivity analysis for offline policy evaluation, as implemented in Jung et al. (2017) <arXiv:1702.04690> based on Rosenbaum and Rubin (1983) <http://…/2345524>.

Imputation the Tidyverse Way (tidyimpute)
Functions and methods for imputing missing values (NA) in tables and list patterned after the tidyverse approach of ‘dplyr’ and ‘rlang’; works with data.tables as well.

Advertisements