Dr Mircea Zloteanu 🍁 🍃Nov 10

#statstab #456 Shall we count the living or the dead?

Thoughts: survival ratio -> if the intervention increases risk of the outcome
risk ratio -> if the intervention reduces risk of the outcome

#causalinference #riskratios #survivalanalysis #estimand

https://arxiv.org/abs/2106.06316v5

Shall we count the living or the dead?

In the 1958 paper "Shall we count the living or the dead?", Mindel C. Sheps proposed a principled solution to the familiar problem of asymmetry of the relative risk. We provide causal models to clarify the scope and limitations of Sheps' line of reasoning, and show that her preferred variant of the relative risk will be stable between patient groups under certain biologically interpretable conditions. Such stability is useful when findings from an intervention study must be generalized to support clinical decisions in patients whose risk profile differs from the participants in the study. We show that Sheps' approach is consistent with a substantial body of psychological and philosophical research on how human reasoners carry causal information from one context to another, and that it can be implemented in practice using van der Laan et al's Switch Relative Risk, or equivalently, using Baker and Jackson's Generalized Relative Risk Reduction (GRRR).

arXiv.org
Dr Mircea Zloteanu 🍁 🍃Oct 27

#statstab #446 {causaldata} Packages of Example Data for The Effect

Thoughts: On your journey to learning Causal Inference you can use some nice datasets to figure out how horrible it can all go.

#causalinference #observational #python #r #DAG #OS

https://github.com/NickCH-K/causaldata

GitHub - NickCH-K/causaldata: Packages of Example Data for The Effect

Packages of Example Data for The Effect. Contribute to NickCH-K/causaldata development by creating an account on GitHub.

GitHub
Dr Mircea Zloteanu 🍁 🍃Oct 22

“Correlation is causation” 😈

New #substack going over the maths of correlation, t-test, and linear models. https://open.substack.com/pub/mzloteanu/p/correlation-is-causation?r=3b457w&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

#correlation #causalinference #effects #pearson #ttest

Correlation *is* causation!

- at least mathematically

Figuring Stuff Out - Dr Mircea Zloteanu
Dr Mircea Zloteanu 🍁 🍃Oct 17

#statstab #440 Computing Statistical Power for the Difference in Differences Design

Thoughts: DiD studies are all the rage in Obs research. But how does the concept of power apply to them?

#poweranalysis #DiD #causalinference #samplesize #observational

https://journals.sagepub.com/doi/10.1177/0193841X251380898

Tom StaffordOct 11

New newsletter! Understanding participation in the X Community Notes system, via my love of data visualisation and stronger causal inference methods!

#DataViz #CausalInference #FactChecking #CommunityNotes

https://open.substack.com/pub/tomstafford/p/community-notes-require-a-community

Dr Mircea Zloteanu 🍁 🍃Oct 9

#statstab #434 Exposing omitted moderators: Explaining why effect sizes differ in the social sciences

Thoughts: Maybe our models are too simple to makdle the generalisable claims we want.

#bias #moderator #causalinference #heterogeneity #effect

https://doi.org/10.1073/pnas.2306281121

Pierre-Simon LaplaceSep 20

🧪 Causal inference is about understanding why things happen, not just what

Alex Andorra talks with Sam Witty about ChiRho & how probabilistic programming is reshaping interventions, counterfactuals, and the future of causal reasoning

🎧https://learnbayesstats.com/episode/141-ai-assisted-causal-inference-sam-witty

#CausalInference #BayesianStatistics #Podcast #DataScience #AIResearch #LearningBayesianStatistics #NewEpisode

jobRxivSep 17

Postdoc in Single-Cell Multi-Omic Gene Regulatory Networks
University of Massachusetts Chan Medical School

Decode #GeneRegulatoryNetwork from #SingleCell multiomics with #CausalInference and #DiffEq as a #postdoc! No biomed bg needed.

See the full job description on jobRxiv: https://jobrxiv.org/job/university-of-massachusetts-chan-medical-...
https://jobrxiv.org/job/university-of-massachusetts-chan-medical-school-27778-postdoc-in-single-cell-multi-omic-gene-regulatory-networks-2/?fsp_sid=2615

Science Jobs - Find science and research jobs

The international job board for scientists, by scientists. Find science jobs in academia or industry: MSc, PhD, Postdoc, Scientist, Faculty and more!

jobRxiv
AnonchegSep 11

P2: #causalinference #causality #inference #statistic #observability #llm #reasoning
| Data types | Requires model integration | Handles via prompting in one model |
```
**LLM Limitations:** LLMs use pattern matching over
explicit causal modeling.
- No explicit causal graphs/mechanisms—only patterns and
correlations.
- Lack modular separation, functions are entwined.
- Risk of hallucinated causal links, unreliable for
interventions.
- Formal counterfactuals need extensive external
scaffolding.

**Fields:**
- **Healthcare:** Predict treatment outcomes (reasoner),
explain intervention effects (explainer), recommend
actions (producer).
- **Economics/Policy:** Assess impacts, clarify causal
pathways, propose policies.
- **Recommendation Systems:** Infer preferences, explain
choices, personalize outputs.

Text of original post: https://try-codeberg.github.io/static/causal-inference.org

AnonchegSep 11

P2: P1: #causalinference #causality #inference #statistic #observability #llm #reasoning
needing rigorous, transparent causality.
- Effective for quick prototyping or low-risk tasks where
simulated causal logic suffices.

```text
| | **Causal Inference Neural Networks** | **Prompt-Engineered Multimodal LLM** |
|--------------+--------------------------------------+-------------------------------------------|
| Causality | Explicit, modeled, testable | Pattern-based, plausible but implicit |
| Reliability | High (given good data/model) | Medium, can produce errors/hallucinations |
| Transparency | Modular, explainable | Opaque, explanation quality varies |
| Scalability | Harder (custom per domain/signal) | Easier (generalizable across domains) |