Here is a decent summary of the advantages and disadvantages of many tools in causal inference (taken from Valentelyte et al. (2021) #econtwitter cc. @causalinf @ez_angus @_WagnerG_ https://t.co/OjoEYPbgdA

Together we competed in today's #3MT @MonashBusiness round and they were all amazing 🙌 I am also humbled and grateful to have been chosen the winner of this round 🙈😅 So thankful to my supervisors and PhD friends @CHE_Monash for helping me practice ❤️❤️❤️

🚨Publication 🚨 We contacted almost every pharmacy in Ireland asking for prices of commonly prescribed drugs and found: -Large variation in prices: top 10% most expensive pharmacies can be over 2x more expensive than the 10% cheapest pharmacies 💊💊💊 https://t.co/yc8AE7O7xm

If for no other reason, this is why you must not vote the Liberal Party back into power: “In a single line item [in the latest budget], the Morrison government defunded Australia’s national prescribing service, NPS MedicineWise (NPS). /2

Patrick McHale of #novartis giving us an overview of gene therapies. So far this #webinar on 'The Challenges of Precision Medicine' has given so much food for thought! @ISPORVicTas @HealthEconNUIG #genetherapy #Pharmaceuticals

#PrecisionMedicine may offer improved Tx options tailored for the individual patient – but what are the challenges of #HEOR? The @nuigalway ISPOR student chapter & @ISPORVicTas will hold a #free webinar on 22Feb to discuss this in the context of #Ireland & #Australia Register👇

Planning a short video for students on how filepaths work. Planning to include: 1. Filepaths on your computer vs. URLs on the internet 2. Relative vs. absolute filepaths 3. Working directories 4. Filepaths in your code 5. Navigating folders with ../ etc. Anything I should add?

NEW: people worry when they hear "40% of hospitalisations are fully vaxxed", but this chart shows that's actually good news. The more people you vaccinate, the higher their share of hospitalisations, but the *total* number in hospital is a fraction of what it would otherwise be

Good times had today at our end of year celebration at the Zoo!

Hire this guy to be in charge of the US public health communication.

#EconTwitter Public Good Alert: I have created an online course in #causalinference (my 2020 lockdown project). The course is based on Mostly Harmless Econometrics and @causalinf 's Mixtape, and covers basics of canonical research designs (IV, RDD, DiD, SC) 1/2

The Omnicron variant is just another example of how COVID will be prolonged if rich nations and Big Pharma keep blocking vaccine distribution.

🚨 Curious about recent advances on applied micro methods 🤓? I'm sharing a doc that I've put together and that lists a bunch of papers such advances. Suggestions are welcome! 🚨 👉 https://t.co/QjegvgUcMK 👈 #EconTwitter #PublicGoods #AppliedMicro #Econometrics

In case you're interested, I wrote a bunch of visualization programs tailored for admin data analysis in Stata. https://t.co/uiWEnD5USj The syntax is a bit quirky, but the code is fast and efficient, requiring little time and memory compared to Stata's native graphing commands.

Okay, so this @Stata tip is a big deal for admin data workflows: As of version 16, Stata allows you to hold 𝗺𝘂𝗹𝘁𝗶𝗽𝗹𝗲 𝗱𝗮𝘁𝗮𝘀𝗲𝘁𝘀 𝗶𝗻 𝗺𝗲𝗺𝗼𝗿𝘆 𝗮𝘁 𝗼𝗻𝗰𝗲. This is done using the command 'frame': sysuse auto, clear frame create fr1 frame fr1: sysuse bplong

#drdid update on #Stata implementation: Its done. I will do some more testing and convert it into some usable form. Doing a full package will take time but I will put online in a week or so. @pedrohcgs @causalinf @nickchk

It's fully-featured and ready to go! The did Stata package allows Stata access to the Callaway and @pedrohcgs R package "did" for estimating difference-in-differences with staggered treatment and covariates. Check it out, and installation instructions, at

Our systematic review and meta-analysis on the volume-outcome relationship for PCI has been published in @HRBOpenRes https://t.co/l4F4V8hncD Looking forward to receiving peer review of our work.

Here's a bunch of @Stata tips for handling large datasets (millions of observations). I wish I knew them when I was starting with admin data analysis...