Carlos E Lourenco (Caê)

On this page What’s the difference between statistical significance and substantial significance? Can we measure substantial significance with statistics? What are all the different ways we can look at model coefficients? Print the object name Use summary() Use tidy() from the {broom} package Use model_parameters() and model_details() from the {parameters} and {performance} packages Make nice polished side-by-side regression tables with {modelsummary} Make automatic coefficient plots with modelplot() from {modelsummary} Plot model predictions and marginal effects Automatic interpretation with {report}

Posted a helpful little set of FAQs about regression for my causal inference class, including illustrations of statistical vs. substantive signficance and all the different things you can do with #rstats model objects

evalsp26.classes.andrewheiss.com/news/2026-02...

Happy to share our recent article on causal inference in science studies. It aims to introduce causal thinking to the science of science community with an example from Open Science.

## Deep Learning-Driven Adaptive Behavioral Correction via Dynamic Causal Inference in Socio-Technical Systems

**Abstract:** This research proposes a novel framework for adaptive behavioral correction within complex socio-technical systems using deep learning and dynamic causal inference. Current…

📜 Paper: https://arxiv.org/pdf/2601.00037

Interested in what's new in causality and causal machine learning?
Check our Causal Python Weekly Newsletter (FREE): https://causalpython.io


5/5

His conclusion is that "causality in physics is (...) indispensable in practice but (...) elusive in principle"

He calls causality "a concept we think we cannot do without, but one that our best equations are surprisingly reluctant to describe."

Would you agree?

4/

Perhaps this difficulty indirectly inspired Bertrand Russell's 1913 statement that "causality is a relic of the past".

But is it?

In his freshly updated paper, Alessandro De Angelis offers us a brief tour of the history of causality in physics, from Galileo to quantum mechanics, and more.

3/

"(...) it is evident that (the) degree of speed will not go on increasing when its cause of increase is taken away"

The idea that causality is somehow "obvious" or "evident" is not new and perhaps, among other things, it reflects a conceptual difficulty in dealing with the topic.

2/

Is Causality a "Working Hypothesis"?

The notion of causality has a turbulent history in physics.

In a posthumously published part of his Two New Sciences, one of Galileo’s fictional protagonists, Salviati, says:

1/

#CausalSky #ScienceSky #EconSky #MLSky

When A/B Tests Aren’t Possible, Causal Inference Can Still Measure Marketing Impact

In many real‑world settings, running a randomized experiment is simply impossible. We’ll walk through Diff‑in‑Diff, Synthetic Control, and Meta’s GeoLift. We show how to prep your data, and …
#hackernews #meta #news

arXiv:2403.06783v1 Announce Type: new Abstract: The Mann-Whitney-Wilcoxon rank sum test (MWWRST) is a widely used method for comparing two treatment groups in randomized control trials, particularly when dealing with highly skewed data. However, when applied to observational study data, the MWWRST often yields invalid results for causal inference. To address this limitation, Wu et al. (2014) introduced an approach that incorporates inverse probability weighting (IPW) into this rank-based statistics to mitigate confounding effects. Subsequently, Mao (2018), Zhang et al. (2019), and Ai et al. (2020) extended this IPW estimator to develop doubly robust estimators. Nevertheless, each of these approaches has notable limitations. Mao's method imposes stringent assumptions that may not align with real-world study data. Zhang et al.'s (2019) estimators rely on bootstrap inference, which suffers from computational inefficiency and lacks known asymptotic properties. Meanwhile, Ai et al. (2020) primarily focus on testing the null hypothesis of equal distributions between two groups, which is a more stringent assumption that may not be well-suited to the primary practical application of MWWRST. In this paper, we aim to address these limitations by leveraging functional response models (FRM) to develop doubly robust estimators. We demonstrate the performance of our proposed approach using both simulated and real study data.

arXiv📈🤖
A doubly robust estimator for the Mann Whitney Wilcoxon Rank Sum Test when applied for causal inference in observational studies
By

Here's another one: www.nature.com/articles/s41.... So basically, it seems @springernature.com requires clinical trials in Scientific Reports to adhere to rigorous standards, but you can still publish an uncontrolled study of a drug, with no registration, control, blinding or whatever.

Hi @springernature.com
How come this article got published in Scientific Reports despite not meeting any of the criteria you claim to use for clinical trials?
pubpeer.com/publications...
#autism

This is an impressive project. My reaction to what it shows though is that survey experiments have gotten out of hand in polisci. I will blog more on this, but I do not think survey experiments are emblematic of the credibility revolution. Some are already interpreting as such, which is a problem.

A blog post giving a more thorough take on survey experiments and the credibility revolution: cyrussamii.com?p=4168

When Evidence Synthesis Obscures: A Critique of Meta-Meta-Analyses – Matthew B. Jané Meta-analyses are often seen as the gold standard of evidence synthesis–systematic, quantitative, and rigorous (at least when done well). So it’s no surprise that some researchers have taken things a ...

"Meta-meta-analyses trade precision & rigor for expediency. If your aim is rigor, there’s no substitute for doing the hard work."

Preach!

I once read a #meta-analysis that mistook SE for SD. Since then I am suspicious of all such studies.

Do the hard work!

matthewbjane.github.io/blog-posts/b...

[2025-12-01] 📚 Updates in #CML

(1) Counterfactual Explanation for Multivariate Time Series Forecasting with Exogenous Variables
(2) A Sensitivity Approach to Causal Inference Under Limited Overlap

🔍 More at researchtrend.ai/communities/CML

On the reading list it goes!

Causal inference and the metaphysics of causation - Synthese The techniques of causal inference are widely used throughout the non-experimental sciences to derive causal conclusions from probabilistic premises. This poses a philosophical question. What in the n...

New paper out in Synthese—a metaphysical theory of causation designed to explain statistical causal inference. Basically a summary of a 100,000-word book (Causation: Science, Statistics and Metaphysics) that'll go into production with CUP soon. Watch this space link.springer.com/article/10.1...

Data Walks Reveal Residents' Mixed Feelings on Privacy How do Long Beach residents feel about data collection in their city? Gwen Shaffer's data walks reveal surprising insights.

Until tech gives more agency to citizens, smart cities are a dumb idea for democracy. "While cities may disclose how they collect data, they rarely offer ways to opt out." "Residents want agency" #privacy #AIEthics

spectrum.ieee.org/smart-city-p...

The default prior for the intercept in both {rstanarm} and {brms} are very wide.

Counterintuitively - being on the logit scale, this is actually translates to a **strong** prior that p(y=1) is near 1 or near 0.

Always check your priors!

#rstats

A quick (1000 words) read to enjoy with your morning coffee or afternoon tea:

"Psychology wants to stay WEIRD, not go WILD"

Why hasn't psychology diversified it samples, methods, theories, etc.? Because it doesn't want to. osf.io/preprints/ps...

#statstab #458 Causal inference for observational data using {modelbased}

Thoughts: IPW, g-computation, and more. Learning OS and ways to compute ATE for (more accurate, but still not great) inference.

#gcomputation #ipw #iptw #observational #inference

easystats.github.io/modelbased/a...

Causal Python || Your go-to resource for learning about Causality in Python A page where you can learn about causal inference in Python, causal discovery in Python and causal structure learning in Python. How to causal inference in Python?

We'll start sending this week's issue today at 9am PT / 12pm ET / 6pm CET

Join 4k+ of top researchers and practitioners for free at CausalPython.io

3/3

#CausalSky

Can Game Theory Help Us with Causal Discovery?

What's Your Guess?

In this week's issue of Causal Python Weekly, expect a solid mix of history, fresh discoveries, and good teaching:

1/

#CausalSky #EconSky #StatSky #MLSky #EpiSky

Grid display of 6 coefficient plots showing the effects of different emotion manipulation instrument types when used to manipulate six different emotions.

We were wrong about the strength of more personalized instruments! Vignette instruments had the largest treatment effects on emotions that we studied, except for anger. Images (we looked photographs from affective image inventories) tended to work well, too.

(9/17)

This paper:

1. Shows that the big challenges in emotions experiments are instrumental variable challenges: weak instruments, violations of the exclusion restriction, compliance.

2. Identifies emotion manipulations that work even in online surveys.

(4/17)

Abstract of a paper written by Amanda Weiss and Ekin Dursun and titled "Robust Emotion Manipulation for Surveys: Evidence from Three Experiments." The abstract reads: "A large number of experiments investigate the effects of emotions on critical political outcomes, including policy attitudes, support for authoritarians, tolerance, and political participation. The success of these experiments depends on emotion manipulations: Manipulations must be strong enough to shift one target emotion while also being specific enough shift other confounders only minimally. In this project, we identify emotion manipulations that fulfill these imperatives. First, using causal graphs, we show that in such experiments, emotions are intermediate outcomes of randomly assigned emotion manipulation instruments—not randomized treatments themselves. Then, we present evidence from three experiments (total N = 6, 649) on the effectiveness of vignettes, autobiographical emotional memory tasks, images, and more for inducing anger, gratitude, fear, political anger, political gratitude, and political cynicism. We show that vignettes are reliable instruments in terms of both strength and specificity. We also investigate compliance with emotion manipulation instruments and find that pre-treatment attitudes toward research may moderate treatment effects.

🚨 Updated working paper!

Ekin Dursun and I ask what instruments best manipulate emotions on surveys (osf.io/56h4g).

We find that vignettes really work! They have large effects on emotions of interest & smaller effects on emotions *not* of interest.

But as always, it's complicated.👇

(1/17)

New paper online!🎉
We introduce a new concept: AI-related conspiracy theory, which claims that powerful humans use AI for malicious purposes or AI itself eventually controls humans.
Yes, this is inspired by the movie “the Matrix”.👻
bpspsychub.onlinelibrary.wiley.com/doi/full/10....

Analysis of Sales Shift in Retail with Causal Impact: A Case Study at Carrefour | Towards Data Science Applying causal inference to measure the effect of product unavailability on retail sales at Carrefour

ICYMI: Thanh Liêm Nguyen's deep dive into applying causal inference to measure the effect of product unavailability on retail sales at Carrefour.