Standard Errors for Calibrated Parameters http://arxiv.org/abs/2109.08109 Calibration, the practice of choosing the parameters of a structural model to match certain empirical moments, can be viewed as minimum distance estimation. Existing standard error formulas for such estimators require a con 📈🤖

One general piece of advice I give students who are coding their first project:

1- write code like you are writing for someone else (cause you are).

2- write code like you’ll have to do many (many!) small variations to your code down the road.

CATE Lasso: Conditional Average Treatment Effect Estimation with High-Dimensional Linear Regression http://arxiv.org/abs/2310.16819 In causal inference about two treatments, Conditional Average Treatment Effects (CATEs) play an important role as a quantity representing an individualized causal ef 📈🤖

"Very few people have died of starvation with money in their pockets," Caldeira wrote to Salon. "Climate change hits hardest those with empty pockets."

www.salon.com/2024/01/12/n...

Long Story Short: Omitted Variable Bias in Causal Machine Learning http://arxiv.org/abs/2112.13398 We derive general, yet simple, sharp bounds on the size of the omitted variable bias for a broad class of causal parameters that can be identified as linear functionals of the conditional expectatio 📈🤖

Great explainer for Diff-in-Diff applications by Jonathan Roth, Pedro Sant’Anna, Alyssa Bilinski and John Poe: www.jonathandroth.com/assets/files... #EconSky 📉📈

Machine Learning for Staggered Difference-in-Differences and Dynamic Treatment Effect Heterogeneity http://arxiv.org/abs/2310.11962 We combine two recently proposed nonparametric difference-in-differences methods, extending them to enable the examination of treatment effect heterogeneity in the s 📈🤖

Hamiltonian Dynamics of Bayesian Inference Formalised by Arc Hamiltonian Systems http://arxiv.org/abs/2310.07680 This paper makes two theoretical contributions. First, we establish a novel class of Hamiltonian systems, called arc Hamiltonian systems, for saddle Hamiltonian functions over infinite 📈🤖

Enhancing Scalability in Bayesian Nonparametric Factor Analysis of Spatiotemporal Data http://arxiv.org/abs/2312.05802 This manuscript puts forward novel practicable spatiotemporal Bayesian factor analysis frameworks computationally feasible for moderate to large data. Our models exhibit signific 📈🤖

New paper out in Nature Climate Change today where we develop the first direct estimates of the social costs of hydrofluorocarbons (SC-HFCs) and the large climate benefits associated with global agreements that phase down their production and consumption https://www.nature.com/articles/s41558-023-01

Polisky: I’m thinking about using one week (total 3hr class time) at the end of my undergrad econometrics class as an intro to ML/AI, with the intended takeaway being “ML/AI is accessible and not scary given what you learned this semester”.

What specific methods/applications would you include?

Yes! Feel free to reach out if you have any questions on the special issue.

I am an agricultural economist who works on various applied economic issues related to agriculture, farm policy, climate change and international development. Most of my publications and their replication packages are at sites.google.com/view/jisangy...