MatchIt - Nonparametric Preprocessing for Parametric Causal Inference

Selects matched samples of the original treated and control groups with similar covariate distributions -- can be used to match exactly on covariates, to match on propensity scores, or perform a variety of other matching procedures. The package also implements a series of recommendations offered in Ho, Imai, King, and Stuart (2007) <DOI:10.1093/pan/mpl013>. (The 'gurobi' package, which is not on CRAN, is optional and comes with an installation of the Gurobi Optimizer, available at <https://www.gurobi.com>.)

Last updated 10 months ago

14.53 score 206 stars 20 packages 2.4k scripts 17k downloads

fastLink - Fast Probabilistic Record Linkage with Missing Data

Implements a Fellegi-Sunter probabilistic record linkage model that allows for missing data and the inclusion of auxiliary information. This includes functionalities to conduct a merge of two datasets under the Fellegi-Sunter model using the Expectation-Maximization algorithm. In addition, tools for preparing, adjusting, and summarizing data merges are included. The package implements methods described in Enamorado, Fifield, and Imai (2019) ''Using a Probabilistic Model to Assist Merging of Large-scale Administrative Records'' <doi:10.1017/S0003055418000783> and is available at <https://imai.fas.harvard.edu/research/linkage.html>.

Last updated 12 months ago

7.92 score 260 stars 1 packages 89 scripts 600 downloads

wru - Who are You? Bayesian Prediction of Racial Category Using Surname, First Name, Middle Name, and Geolocation

Predicts individual race/ethnicity using surname, first name, middle name, geolocation, and other attributes, such as gender and age. The method utilizes Bayes' Rule (with optional measurement error correction) to compute the posterior probability of each racial category for any given individual. The package implements methods described in Imai and Khanna (2016) "Improving Ecological Inference by Predicting Individual Ethnicity from Voter Registration Records" Political Analysis <DOI:10.1093/pan/mpw001> and Imai, Olivella, and Rosenman (2022) "Addressing census data problems in race imputation via fully Bayesian Improved Surname Geocoding and name supplements" <DOI:10.1126/sciadv.adc9824>. The package also incorporates the data described in Rosenman, Olivella, and Imai (2023) "Race and ethnicity data for first, middle, and surnames" <DOI:10.1038/s41597-023-02202-2>.

Last updated 5 months ago

7.60 score 128 stars 131 scripts 541 downloads

MNP - Fitting the Multinomial Probit Model

Fits the Bayesian multinomial probit model via Markov chain Monte Carlo. The multinomial probit model is often used to analyze the discrete choices made by individuals recorded in survey data. Examples where the multinomial probit model may be useful include the analysis of product choice by consumers in market research and the analysis of candidate or party choice by voters in electoral studies. The MNP package can also fit the model with different choice sets for each individual, and complete or partial individual choice orderings of the available alternatives from the choice set. The estimation is based on the efficient marginal data augmentation algorithm that is developed by Imai and van Dyk (2005). "A Bayesian Analysis of the Multinomial Probit Model Using the Data Augmentation." Journal of Econometrics, Vol. 124, No. 2 (February), pp. 311-334. <doi:10.1016/j.jeconom.2004.02.002> Detailed examples are given in Imai and van Dyk (2005). "MNP: R Package for Fitting the Multinomial Probit Model." Journal of Statistical Software, Vol. 14, No. 3 (May), pp. 1-32. <doi:10.18637/jss.v014.i03>.

Last updated 5 months ago

6.99 score 12 stars 43 scripts 1.9k downloads

emIRT - EM Algorithms for Estimating Item Response Theory Models

Various Expectation-Maximization (EM) algorithms are implemented for item response theory (IRT) models. The package includes IRT models for binary and ordinal responses, along with dynamic and hierarchical IRT models with binary responses. The latter two models are fitted using variational EM. The package also includes variational network and text scaling models. The algorithms are described in Imai, Lo, and Olmsted (2016) <DOI:10.1017/S000305541600037X>.

Last updated 4 months ago

5.38 score 25 stars 24 scripts 271 downloads

experiment - R Package for Designing and Analyzing Randomized Experiments

Provides various statistical methods for designing and analyzing randomized experiments. One functionality of the package is the implementation of randomized-block and matched-pair designs based on possibly multivariate pre-treatment covariates. The package also provides the tools to analyze various randomized experiments including cluster randomized experiments, two-stage randomized experiments, randomized experiments with noncompliance, and randomized experiments with missing data.

Last updated 3 years ago

5.25 score 13 stars 23 scripts 328 downloads

RCT2 - Designing and Analyzing Two-Stage Randomized Experiments

Provides various statistical methods for designing and analyzing two-stage randomized controlled trials using the methods developed by Imai, Jiang, and Malani (2021) <doi:10.1080/01621459.2020.1775612> and (2022+) <doi:10.48550/arXiv.2011.07677>. The package enables the estimation of direct and spillover effects, conduct hypotheses tests, and conduct sample size calculation for two-stage randomized controlled trials.

Last updated 2 years ago

4.60 score 4 stars 4 scripts 139 downloads