Data Scientist, Economist, Researcher. Like = bookmark.
Zurich, Switzerland
Joined October 2010
- Tweets139
- Following194
- Followers863
- Likes775
Matteo Courthoud retweeted
On citing research software - I really appreciate what @davidroodman is doing in the abstract of his papers.
It's just a quick footnote but makes sure that the people supporting the software behind his research are recognized!
@ArielKarlinsky @VincentAB @soodoku
I think people don't fully appreciate how much effort goes into creating and maintaining good R/Stata packages.
Folks like @lrberge (fixest) and my student Mauricio Bravo (gtools, Stata honestdid), among many others, are true silent heroes.
🍺 to all the stats sw developers!
Matteo Courthoud retweeted
I'm looking for an economics (or related) PhD intern to work with me at Microsoft (in Seattle) for the summer! If you're interested in building new causal inference tools and have interest/experience in tech, IO, and/or econometrics, please reach out!
Hi all!
I am trying something new: a weekly list of my causal inference reads, new and old stuff. I guess you could call it a newsletter, but it's rather a commitment device for me. Still, I hope it can be useful to others as well.
Enjoy! 🤗
medium.com/@matteo.courthoud…
Hi all!
I just collected a lot of causal inference resources in a single repo. It contains books, lectures, software, blogs, papers, ... It's still a work in progress, but happy if anyone wants to collaborate! Enjoy 🤗
github.com/matteocourthoud/a…
Matteo Courthoud retweeted
My lecture notes on causal inference
Look at what I found on arXiv today 🤩 @pengding00 arxiv.org/abs/2305.18793
Matteo Courthoud retweeted
After a long and unsuccessful search for a statistical inference and regression textbook at the right level for our PhD students, I finally decided to write up my lecture notes as a book.
The book is publicly available if you are interested:
mattblackwell.github.io/gov2…
Matteo Courthoud retweeted
I'm teaching a new grad applied metrics course this spring; inspired by @paulgp, I've decided to post slides here
First, Ch. 1-3: a review of regression basics and discussions of design- & model-based ID
dropbox.com/s/8gx1oj69vz9n8c…
dropbox.com/s/z55anktz4anht2…
dropbox.com/s/8jnlcjshek8vwx…
Matteo Courthoud retweeted
3 years ago, I took my methods comprehensive exam just as everything was shutting down.
To prep, I made a cheatsheet that quickly got out of hand and now stands at ~130 pages of notes on econometrics / causal inference / machine learning.
apoorvalal.github.io/methods…
Matteo Courthoud retweeted
I'm looking for a summer intern to work with me and @demirermert to study firms' cloud computing productivity/efficiency using a large (many TB) and unique dataset. Please apply and if you do, please also send me your CV at both emails on my website careers.microsoft.com/us/en/…
New post out!
I have been asked many times for resources to approach or study causal inference, so I collected all the *free* resources I know in a single place. It is a very personal list, related to my background and areas of expertise. Enjoy! 🤗
medium.com/p/a54f1621d455
StableDiffusion is an incredible tool to generate article covers. Styling plots as paintings is a pleasure for the eye and a great satisfaction for people with no artistic skills (me). Here is a restyled cover of one of my old articles on @TDataScience
towardsdatascience.com/9b06e…
Matteo Courthoud retweeted
Double/Debiased ML (Chernozhukov et al, 2016) is a fascinating tool for CATE estimation. Although the theory is pretty intuitive, I think few appreciate what it is really doing, so here is a visual guide for. 🧵
TL;DR, Double-ML can be viewed as a derivative finder.
Matteo Courthoud retweeted
Hi #EconTwitter!
I am on the #EconJobMarket this year. Time for a thread about my JMP.
1/N
A prof once told me that there are two kinds of econometric readers: those that read the text and those that read the equations. I am one of the former and found this book invaluable during my PhD! (free version available on Bruce's website)
My twin Econometrics textbooks are now available! amazon.com/Econometrics-Bruc… #EconTwitter
Matteo Courthoud retweeted
Synthetic control methods have grown to become one of the more popular causal-inference techniques in industry contexts; here's a detailed overview of how they work, courtesy of @MatteoCourthoud. buff.ly/3SKboQh
New post out!
This week I wrote a short post on the Bayesian Bootstrap, a simple but powerful extension of the Bootstrap that avoids some of its corner cases. Enjoy 🤗
#datascience #statistics #causalinference
towardsdatascience.com/6ca4a…
New post out!
This week, I wrote a "short" post on synthetic control. Also, I couldn't resist giving it a synth retro vibe and ended up talking about cars, Miami and neon colors. Enjoy 🤗
#causalinference #datascience #statistics
towardsdatascience.com/dd9a2…
Matteo Courthoud retweeted
Here is a new chapter about synthetic-diff-in-diff. Really creative idea on recasting both SC and DID models as weighted linear regression so that we can merge both. Writing this sure taught me a lot about models for panel data.
matheusfacure.github.io/pyth…
