#statstab #395 The n-of-1 randomized controlled trial: clinical usefulness

Thoughts: Could RCTs comprised of 1 participant be useful? Maybe! And more so than large sample observational studies.

#Nof1 #RCTs #causalinference #research #methods #clinical

https://pubmed.ncbi.nlm.nih.gov/2297206/

#statstab #394 Difference-in-Differences Estimation

Thoughts: A bit of love for the python coders. DiD with lots of examples and estimators.

#did #python #guide #observational #TWFE #causalinference

https://py-econometrics.github.io/pyfixest/difference-in-differences.html#pointwise-vs-simultaneous-inference-in-event-studies

It’s great to see causal Inference methods being used for this determination. Are better algorithms (than the near-far matching used) available that might be used in a judicial process causal digital twins to ameliorate these and other injustices in the future? Of course, getting rid of the bail system would make it moot.

#causalInference #causation #legal #justice

From: @hrdag
https://mastodon.social/@hrdag/114902611019230490

#statstab #392 Statistically Efficient Ways to Quantify Added Predictive Value of New Measurements (forum thread)

Thoughts: Forums can be great for asking the author for exact answers to complex questions

#modelselection #causalinference #prediction #bias #information

https://discourse.datamethods.org/t/statistically-efficient-ways-to-quantify-added-predictive-value-of-new-measurements/2013/1

#statstab #391 {sensemakr} Sensitivity Analysis Tools for OLS

Thoughts: No unobserved variables is an untestable assumption, but you can quantify the robustness of your ATE.

#R #causalinference #observational #inference #confounding #bias #sensitivity

https://carloscinelli.com/sensemakr/

#statstab #387 Give Your Hypotheses Space!

Thoughts: "It’s tempting to throw a bunch of variables...into a model
...but proceed at your own caution!"

#Mbias #causalinference #collider #moderator #confounder #regression #r #DAG

https://brian-lookabaugh.github.io/website-brianlookabaugh/blog/2025/mutual-adjustment/

#statstab #383 Berkson's paradox

Thoughts: aka Berkson's bias, collider bias, or Berkson's fallacy. Important for interpreting conditional probabilities. Can produce counterintuitive patterns.

#paradox #collider #bias #inference #causalinference

https://en.m.wikipedia.org/wiki/Berkson's_paradox

So far at this conference I have seen reports of true experiments, natural experiments, difference in difference analysis and regression discontinuity design - but no instrumental variable analysis

I wonder why?

I was hoping for the full set of causal inference methods

What are people’s fave methods for this situation:

At t0, all units are untreated.

As time goes on, individual units are one by one selected for treatment, on an expert’s assessment of their potential improvement under treatment.

How to measure the treatment effect, either over all units or ideally the treatment effect on each unit?

Oh, for extra fun, they’re probably not independent

Hello SFBA! I’ve been wistfully thinking of switching over here for a while and recent fosstodon choices gave me the push I needed. So #introduction time!

I’m from #SanFrancisco and moved back here after some wandering. Raising two kids and a dog. Working in tech (sigh) but on #sustainability at least.

Interested in and post about #CausalInference, #Statistics, #Politics, #Policy, #Climate, #Energy, #Dogs, #Crafting and #Parenting

To fully realize the potential of our clinical trials, we must go beyond randomization, and use causal inference and pharmacometric modelling and simulation. Advancing both we show that non-linear mixed effects modelling implements the equivalent of standardization in causal inference. Dive into this if you're into #causal #causalinference #DAGs #pharmacometrics, or clinical development #stats.

https://doi.org/10.1002/psp4.13239

I don't think I wrote a new #introduction when I migrated from .social.
I'm a #computational #InfectiousDisease #epidemiologist and #biostatistician. I work on #CausalInference and #NetworkScience methods in ID Epi and #DiseaseEcology #DisEcol

I'll be at #Neurips2022 Tues. 11/29 for our "oral-designated" poster on Empirical Gateaux Derivatives for Causal Inference!

https://arxiv.org/abs/2208.13701

We study numerical differentiation to obtain influence functions for debiased causal inference. We show:
- basic characterization: *what* estimator does finite differences compute?
- rates of computational approx. to preserve stat. rates
- usefulness for "custom" estimators like constrained MDPs

#intro I’m a veterinarian & infectious disease epidemiologist working at the intersection of epi and tech.

My career looks like I played Mad Libs as a kid and then stubbornly followed through on it — the alphabet soup of my degrees are the points of my (not so) random walk.

I graze at the STEM buffet by leading cross-disciplinary teams to solve challenges in public health.

#causalinference #dzmodeling #zoonoses #OneHealth #ecology #PublicHealth #RiskMitigation Non-traditional veterinarians

Hello fellow Mastodonians,

I'm an #epidemiologist with #ADHD at the University of Leeds. I think epidemiology is the world's greatest profession, even though most people think it involves studying skin &/or epidurals.

Most of my content is either about the awesomeness of Epi, the weirdness of ADHD, geeky stuff about #CausalInference, or angry stuff about the culture in #academia.

My proudest moment in 12+ years on Twitter was making the meme below.

#Introduction
#EpiVerse
#ScienceMastodon

Upgrade your #causalinference arsenal.

A revision of our book "Causal Inference: What If" is now available

https://hsph.harvard.edu/miguel-hernan/causal-inference-book/

Thanks to everyone who suggested improvements, reported typos, and proposed new citations and material.

Enjoy the #WhatIfBook.

Also, it's free.

#introduction time!

I do #appliedmath at Dartmouth College. I am all about using #math to model #complexsystems + #networks in #compbio, #compneuro & #compsoc, and to improve methods in #datascience and #ml. (Have worked on #emergence of correlation patterns and #causalinference and now getting into #explanaible #machinelearning for #publichealth / #mentalhealth.)

Would love to connect with the #mastodonscience crowd, #womeninmath, #womeninstem, #python, #dataviz folks, and fellow #cat lovers!

I had a Twitter account for 9 years mainly using it to better understand new areas in science like #causality #causalinference .
My PhD is in #immunology which came in handy during the #COVID #pandemic .
For 25 years or so I have been working on #congenitalheartdisease #BirthDefects and #cardiogenetics