@ProfEmilyOster Good point. I did not see the discussions of sample size, significance level, potential selection bias, and surprisingly, no mention about the baseline effect (people who never drink) in the report (or maybe I missed it?).
Here are the first five sets of slides:
01 Introduction: https://t.co/PIiBqLRIDB
02 Classical 2x2 setup: https://t.co/SH7w5h7MTk
03 Clustering issues: https://t.co/2v72H48HhW
04 Functional form: https://t.co/1qld58HTMI
05 Covariates: https://t.co/4MsX2n6j7w
A new IV estimator that is robust to weak instruments and unknown control variables in high-dimensional model. In November issue, by FAN, Qingliang and WU, Yaqian https://t.co/gf9nrtKvZR
Strong evidence of hot hand performance found both across datasets and within individuals. In November issue, by Joshua B. Miller (@jben0) and Adam Sanjurjo https://t.co/OLGZMhW0sK
Our paper, "On the instrumental variable estimation with many weak and invalid instruments" is published in the September issue of JRSSB. https://t.co/4VpfbD4lha
Our paper "A Heteroskedasticity-Robust Overidentifying Restriction Test with High-Dimensional Covariates" is now available as Open Access in Journal of Business & Economic Statistics!
https://t.co/4qsU64LHwp
I'm so glad that the paper was recently accepted by JBES. I got many useful feedbacks from friends and the editorial teams. Check out the most recent version at https://t.co/PCRTtrBHbZ
@CombeJu OMG this is so sad to hear. I met Yinghua once during a visit in Stanford almost ten years ago. After that I have read many of his wonderful papers and then all of sudden this sad news.
In a recent paper, we provide a robust estimator (WIT) when instrumental variables might be weak and invalid, and the invalidity is not assumed a priori.
https://t.co/JaZx2a4SIn