R & Causal Inference

Welcome!

I’m Yosuke Abe, a private-sector think tank analyst based in Tokyo, Japan.

This page is dedicated to notes and tutorials on R, econometrics, and causal inference. Here I also document updates and practical guides for open-source tools I build, including the coresynth package.

📦 Featured Package: {coresynth}

Fast Synthetic Control Methods in R

{coresynth} provides a high-performance, unified interface for the Synthetic Control Method (SCM) and its modern extensions. By moving computational bottlenecks to C++ via RcppArmadillo, it achieves significant speedups compared to pure-R alternatives—making iterative inference and simulation studies substantially faster.

⚡ High Performance: C++ core delivers substantial speed improvements for heavy optimization routines.
🧩 6 Estimators, 1 Interface: Estimate standard SCM (scm), Synthetic DiD (sdid), Generalized SCM (gsc), Matrix Completion (mc), Time-Aware SCM (tasc), and Synthetic Interventions (si) with a single function scm_fit().
🔄 Versatile Adoption Settings: Native support for both sharp treatment and staggered adoption designs.
📊 Comprehensive Workflow: Built-in methods for visualization (plot()), conformal inference (conformal_inference()), placebo checks, and JSON export (export_json()) for reproducible research.

CRAN GitHub Docs (pkgdown) Getting Started

Installation

# Install the released version from CRAN
install.packages("coresynth")

# Or install the development version from GitHub
# pak::pkg_install("yo5uke/coresynth")

📜 Articles & Guides

Implementing the Synthetic Control Method in R with {coresynth}

A comprehensive guide to estimating, plotting, and conducting placebo inference for the synthetic control method in R using the high-performance {coresynth} package.

Nov 2, 2026

Feedback & Community

Bug reports, feature suggestions, and pull requests for {coresynth} are very welcome! Feel free to open an issue on GitHub Issues or reach out on X (@5uke_y).

--- title: "R & Causal Inference" subtitle: "Notes on econometrics, causal inference methods, and open-source tools in R." listing: id: en-posts contents: "posts/**/index.qmd" sort: "date desc" type: default categories: true sort-ui: false filter-ui: false feed: true title-block-banner: true toc: false comments: false --- ::: {.home-intro} ::: {.fs-3 .fw-bold .mb-3} Welcome! ::: I'm **Yosuke Abe**, a private-sector think tank analyst based in Tokyo, Japan. This page is dedicated to notes and tutorials on {{< fa brands r-project >}} R, econometrics, and causal inference. Here I also document updates and practical guides for open-source tools I build, including the [**coresynth**](https://github.com/yo5uke/coresynth) package. ::: ## 📦 Featured Package: {coresynth} ::: {.coresynth-banner} ### Fast Synthetic Control Methods in R ::: {.badges} [![CRAN status](https://www.r-pkg.org/badges/version/coresynth)](https://CRAN.R-project.org/package=coresynth) [![dev version](https://img.shields.io/github/r-package/v/yo5uke/coresynth?label=dev%20version&color=blue)](https://github.com/yo5uke/coresynth) [![R-CMD-check](https://github.com/yo5uke/coresynth/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/yo5uke/coresynth/actions/workflows/R-CMD-check.yaml) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) ::: ::: {.coresynth-lead} **{coresynth}** provides a high-performance, unified interface for the **Synthetic Control Method (SCM)** and its modern extensions. By moving computational bottlenecks to C++ via `RcppArmadillo`, it achieves significant speedups compared to pure-R alternatives—making iterative inference and simulation studies substantially faster. ::: ::: {.coresynth-features} - **⚡ High Performance**: C++ core delivers substantial speed improvements for heavy optimization routines. - **🧩 6 Estimators, 1 Interface**: Estimate standard SCM (`scm`), Synthetic DiD (`sdid`), Generalized SCM (`gsc`), Matrix Completion (`mc`), Time-Aware SCM (`tasc`), and Synthetic Interventions (`si`) with a single function `scm_fit()`. - **🔄 Versatile Adoption Settings**: Native support for both sharp treatment and staggered adoption designs. - **📊 Comprehensive Workflow**: Built-in methods for visualization (`plot()`), conformal inference (`conformal_inference()`), placebo checks, and JSON export (`export_json()`) for reproducible research. ::: ::: {.coresynth-actions} <a href="https://cran.r-project.org/web/packages/coresynth/index.html" class="btn btn-outline-primary btn-sm" target="_blank" rel="noopener noreferrer"><i class="fa-solid fa-box-open"></i> CRAN</a> <a href="https://github.com/yo5uke/coresynth" class="btn btn-outline-primary btn-sm" target="_blank" rel="noopener noreferrer"><i class="fa-brands fa-github"></i> GitHub</a> <a href="https://yo5uke.com/coresynth/" class="btn btn-outline-primary btn-sm" target="_blank" rel="noopener noreferrer"><i class="fa-solid fa-file-lines"></i> Docs (pkgdown)</a> <a href="posts/coresynth_scm/index.qmd" class="btn btn-primary btn-sm"><i class="fa-solid fa-book-open"></i> Getting Started</a> ::: ::: {.coresynth-install} ::: {.install-label} Installation ::: ```r # Install the released version from CRAN install.packages("coresynth") # Or install the development version from GitHub # pak::pkg_install("yo5uke/coresynth") ``` ::: ::: ## 📜 Articles & Guides ::: {#en-posts} ::: <div class="spacer"></div> ::: {.callout-note} ## Feedback & Community Bug reports, feature suggestions, and pull requests for `{coresynth}` are very welcome! Feel free to open an issue on [GitHub Issues](https://github.com/yo5uke/coresynth/issues) or reach out on [X (\@5uke_y)](https://x.com/5uke_y). :::

Categories

📦 Featured Package: {coresynth}

Fast Synthetic Control Methods in R

📜 Articles & Guides

Implementing the Synthetic Control Method in R with {coresynth}