# Vincent Arel-Bundock

> Academic website and blog of Vincent Arel-Bundock.

## Pages

- [Blog](https://arelbundock.com/blog.html)
- [Books](https://arelbundock.com/books.html): Arel-Bundock, Vincent. 2026. CRC Press.
- [Code](https://arelbundock.com/code.html): compute and plot predictions, slopes, marginal means, and comparisons (contrasts, risk ratios, odds ratios, etc.) for over 70 classes of statistical models in R. Conduct linear and non-linear hypothesis tests, as well as equivalence tests using the delta method.
- [Data](https://arelbundock.com/data.html): This project aims to make available firm-level information about every insurance contract issued, financing project initiated, and insurance claim settled by the US Overseas Private Investment Corporation.
- [Blogue](https://arelbundock.com/fr/blogue.html): Tous les billets, du plus recent au plus ancien.
- [Code](https://arelbundock.com/fr/code.html): pour calculer et visualiser des prédictions, des pentes, des moyennes marginales et des comparaisons (contrastes, rapports de risque, rapports de cotes, etc.) pour plus de 70 classes de modèles statistiques en R. Permet de réaliser des tests d'hypothèses linéaires et non…
- [Donnees](https://arelbundock.com/fr/donnees.html): Ce projet vise à rendre accessible l'information au niveau de l'entreprise sur chaque contrat d'assurance émis, chaque projet de financement initié et chaque réclamation réglée par l'Overseas Private Investment Corporation des États-Unis.
- [Vincent Arel-Bundock](https://arelbundock.com/fr/): Je suis professeur à l'Université de Montréal, où j'enseigne l'économie politique comparée et internationale. Je m'intéresse particulièrement à la politique de la fiscalité internationale et de l'investissement direct à l'étranger, mais j'ai aussi travaillé sur la politique…
- [Livres](https://arelbundock.com/fr/livres.html): Arel-Bundock, Vincent. 2026. CRC Press.
- [Recherche](https://arelbundock.com/fr/recherche.html): Les données et le code utilisés dans mes recherches sont généralement archivés par l'Open Science Foundation.
- [Vincent Arel-Bundock](https://arelbundock.com/): I am a Professor of Political Science at the Universite de Montreal, where I read on comparative and international political economy. I am particularly interested in the politics of international taxation and foreign direct investment, but I have also worked on monetary policy…
- [Directed Acyclic Graphs](https://arelbundock.com/posts/acmq_en_06_dag/): This notebook offers an ultra-simple overview of Directed Acyclic Graphs (DAGs). My goal is to introduce readers who are unfamiliar with DAGs to tools which can help answer three critical questions:
- [What to do with age? Linear, Discrete, Both, or Spline](https://arelbundock.com/posts/age_linear_discrete/): In
- [Distribution-Free Prediction Intervals with Conformal Inference using `R`](https://arelbundock.com/posts/conformal/): Warning: This notebook is not authoritative. I am very new to conformal inference, and this is just my attempt to work things out (in public). Let me know if you spot mistakes.
- [Nesting with data.table and tidyverse](https://arelbundock.com/posts/datatable_nesting/): The nest/unnest programming pattern can be a useful way to organize your data analyses in R. The idea is to store a series of objects (e.g., datasets, models, summaries) in a "list-column." A list-column is simply a column in your data frame where each entry is a list. Each of…
- [Rowwise operations with data.table](https://arelbundock.com/posts/datatable_rowwise/): This notebook illustrates how one can apply a function to every
- [Which `R` packages do scientists use?](https://arelbundock.com/posts/dataverse_r/): I downloaded r n_scripts R scripts from r n_projects projects hosted by the The Dataverse Project. This notebook reports usage statistics for R packages in this large sample of real-life scientific applications.
- [Simulation-based power calculations and model assessment with R and DeclareDesign](https://arelbundock.com/posts/declare_design/): The DeclareDesign package for R is a flexible tool to
- [Event-study DiD with staggered treatment design](https://arelbundock.com/posts/dind/): This is another post in my series of attempts to learn the data.table package for R and to get more comfortable with base R graphics. Today, I reimplement the data generating process and one of the models in this excellent blog post by Andrew Baker:
- [Distribution regression in R](https://arelbundock.com/posts/distribution_regression/): This notebook introduces "Distribution Regression", an alternative to quantile regression which can be used to explore treatment effect heterogeneity.
- [`data.table`, `base`, `dplyr`, `pandas`, and `polars`](https://arelbundock.com/posts/dt_tb_df/): This page presents a side-by-side comparison of common data manipulation operations in five idioms: data.table, base, dplyr, polars, and pandas. This allows you to compare syntax and understand how to accomplish tasks across these popular frameworks.
- [Is Dunning-Kruger a statistical artefact?](https://arelbundock.com/posts/dunning_kruger/): In a seminal study, @Kruger_Dunning_1999 found that:
- [Staggered Difference-in-Differences with Two-Way Fixed Effects and Interactions](https://arelbundock.com/posts/extendedtwfe/): Recently, Wooldridge shared a working paper titled
- [Frontdoor adjustment for causal inference: A primer with examples in `R`](https://arelbundock.com/posts/frontdoor/): This notebook has 3 objectives:
- [Marginal Structural Models: A Simulation With `R` and `data.table`](https://arelbundock.com/posts/marginal_structural_models/): Andrew Heiss recently published a series of
- [`marginaleffects` 1.0.0](https://arelbundock.com/posts/marginaleffects100/): Big news! marginaleffects 1.0.0 for R is out. It's a big number and it feels like an important moment, so I wrote a blog.
- [Prior Predictive Checks with `marginaleffects` and `brms`](https://arelbundock.com/posts/marginaleffects_priors/)
- [Sample Size Calculations in `R`: Money vs. Power](https://arelbundock.com/posts/money_and_power/): My colleagues and I have argued that
- [Notes on Hainmueller, Mummolo & Xu: How Much Should we Trust Estimates from Multiplicative Interaction Models?](https://arelbundock.com/posts/non_linear_interactions/): Political Scientists absolutely looove regression models with multiplicative interactions [@brambor2006;@Bra2004]. In "How Much Should we Trust Estimates from Multiplicative Interaction Models?" Hainmueller, Mummolo, and Xu (HMX) criticize the standard practice of entering these…
- [Consistent figures in Quarto](https://arelbundock.com/posts/quarto_figures/): I've been struggling to correctly size my ggplot2 or base plots in Quarto documents. The main problem I encounter is that when I change the width or size of a figure, the text in figures also changes in size, which makes the document look very inconsistent.
- [Regression adjustment in experiments](https://arelbundock.com/posts/regression_adjustment/): The other day,
- [Statistical Rethinking 2 with Stan and the tidyverse](https://arelbundock.com/posts/rethinking2/): I've been trying to replicate (nearly) all the models in Richard McElreath's
- [Making Sense of Sensitivity: Extending Omitted Variable Bias](https://arelbundock.com/posts/robustness_values/): @CinHaz2020 ask: How strong do omitted confounders have to be in order to change our coefficient estimate by q%? To answer this question, we start with a familiar setup, where we want to estimate the effect of treatment $D$ on outcome $Y$ in the presence of confounder $Z$. The…
- [Analyzing data in the terminal with vim and byobu](https://arelbundock.com/posts/vimbyobu/): This post describes how I conduct interactive data analysis from the terminal using vim and byobu. Check out this YouTube video to see the setup in action:
- [Research](https://arelbundock.com/research.html): The data and code used in my research are usually archived by the