We've had no data on real-world EV+P use for mUC, until now. In @EUplatinum we show rapid dissemination of EV+P in practice. As of 3/31/24, <4 mo after @US_FDA full approval, EV+P accounted for ~50% of 1L tx starts, supplanting platinum-chemo (23%).
https://t.co/ZP0iPtJcno
Esta ⬇️ es una gráfica publicada en la cuenta oficial del @GobiernoMX
Claramente ahora hay #MenosHomicidiosEnMéxico ✅
¿O NO?
Si observas la gráfica CON ATENCIÓN, ¿qué cosas "extrañas" encuentras? 👀
Abrimos 🧵 de nuestra investigación
https://t.co/4rzcHEC2t2
🔴 En @pajaropolitico manifestamos nuestra solidaridad total con la periodista @Nataliekitro, cuyos datos personales fueron expuestos por el presidente @lopezobrador_ y quien ha sido sometida al acoso e intimidación desde las mañaneras y utilizando todos los recursos públicos.
My son has just started calculus, and I asked him what the relationship was between the gradients of the tangent and the normal to a curve at a given point. His first reply was, "They are perpendicular." I've noticed many times that something one gains with experience ... 1/7
Happy to announce our work on distribution-free calibration of CATE predictors using causal isotonic cross-calibration has been accepted to #ICML2023! Looking forward to presenting our findings and connecting with fellow researchers in Hawaii. #ICML#causaltwitter#causalinf
THE WORLD'S SMARTEST MAN DOESN'T WANT YOU TO READ THIS ON TWITTER
This will be a long thread. I'm going to put a link at the end—the end because if I put it at the beginning, Twitter will throttle my engagement.
It will tell you it is an unsafe link, even though it isn't.
New paper!!! Causal Isotonic Calibration for HTEs! We propose new nonparametric methods for calibrating predictors of CATEs. Our methods can be wrapped around any black-box learning algorithm to provide strong distribution-free calibration guarantees. https://t.co/8VmGHADB7J
People are sharing this thread around a lot, and I have to say that it's extremely unfair and mostly incorrect when it comes to the specifics of the Cochrane review
❓#STATquestions📈Si queremos comparar una variable numérica (moderadamente sesgada a la derecha) entre dos grupos, y nuestra muestra es grande, ¿cuál es la mejor prueba estadística para compararlas?
Two important pre-prints out on omicron neuts out today.
Here’s how I would interpret these results in light of what we know about correlates of protection. 1/n
https://t.co/rcoGNx3elM
Right now, in the USA, 99% of people being hospitalized & dying from COVID-19 are those who chose not to be vaccinated.
This confirms that whoever’s been advising you to decline the Vaccine, does not value your health or longevity.
A form of biological “unnatural” selection.
Y @CitlaHM sencillamente MIENTE al decir que más de la mitad de la población ha sido vacunada.
Por favor no compartan este tuit, porque anexo una gráfica donde se ve como apenas el 27% ha sido vacunada (y con dosis completas solo el 16%).
No hagamos quedar mal a la Citla.
Finally—some news about J&J:
-94% of breakthrough infections (including w/ delta) are mild, 4% moderate, 2% severe
-data from 400k HCWs in South Africa
-claims immunity improves over time
In my mind this means J&J retains effectiveness against delta BUT
https://t.co/mdFed3NEOK
Interested in learning about causal inference, machine learning and how it all fits together?
Come take a short course this summer with @mcaronebstat, @ildiazm, and me at the @UWBiostat Summer Institutes!
https://t.co/CaKbhUDtAs
#causaltwitter#epitwitter
Spread the word!
This is literally what happens when we’re just trying to live in joy... she screamed, “do you live in this neighborhood!?”
And it happens all the time. 🤬
Hace dos años lanzamos @RadarDeMediosMx, una herramienta para detectar los temas más recurrentes de los principales 37 medios de comunicación de México.
Hoy, la segunda parte de esa herramienta: el rastreo de las mañaneras de AMLO.
🧵🇲🇽
https://t.co/fXGrdSccsd