just a bit more detail on the i3 BigQuery workspace: problems we're trying to solve: ▶️datasets are getting unwieldy. OpenAlex is 400G compressed, takes hours to download / inflate / un-json / assemble. then you merge it... ▶️merging is fraught with identifier mismatches,

Happy to see our WP w Shogo Sakabe and @deweinstein (so many years in the making!) out. We examine the role of codifying knowledge in the spread of the Industrial Revolution. A little thread. 1/N

If applied researchers remember one thing from this whole discussion, please let it be this: There is no plug-and-play research method. You can't just apply an empirical strategy off the shelf, without reflection, and assume it will work. You have to think critically about what

1/excited to start at @UChicago @ChicagoBooth with my first NBER WP (!) with @Econ_4_Everyone and @GaryCharness on AI and experimental methods! https://t.co/wQMMwfK5MP more below

Just posted: @Arnold_Ventures has put together guidance for conducting power analyses of various causal research designs (RCTs and non-RCTs). Huge thanks to @BillingsEcon, Jonah Gelbach, and @KSchnepel for their help with this. https://t.co/t41hPcDdI6

Time to celebrate! “DID estimators of intertemporal effects” accepted at @restatjournal, and very very fast did_multiplegt_dyn Stata & R commands available from SSC & CRAN, thanks to Mélitine Malézieux @fe_knau @diegociccia1 & @DSDoulo! Celebratory thread! https://t.co/i0lwPE6mtV

If you are looking for Public Datasets to work on Data Science & Machine Learning. Here are 7 Free Data Sources where you can find one for your next Project: 🧵👇

Forthcoming in The Review of Economics and Statistics, our paper (with Kyle Schirmann, Christos Makridis and @TarunKhannaHBS) presents arguably one of the first set of experimental findings on how hybrid work affects individual outcomes. Link to paper: https://t.co/dCAf7hpEvO

You don't need to know programming or GIS to use geospatial data. Here are 3 resources to get you started:

📣Our 🆕 paper Causal Inference is Not Just a Statistics Problem is out! @malco_barrett, @travisgerke, and I show that you can have 4 data sets with identical summary stats & visuals but very different data generating mechanisms-statistics alone can't tell you what to adjust for!

📢 To patent analysts and data enthusiasts Check out my paper with @GeorgeAbiYoune1 "Replicable Patent Indicators Using the Google Patents Public Datasets". It provides an introduction to #patent #data using #BigQuery 🤓 ➡️ https://t.co/Ub4IeOrVda + https://t.co/XijwyZ8cay.

I announced 2 packages for Stata that speed up Sergio Correia's amazing reghdfe by ~10X. "jl" bridges to Julia. reghdfejl runs on top. It mimics reghdfe, but calls Julia. See https://t.co/RfS9puwG9H…. Please follow directions under Installation in "help jl".

You've seen the live performance. You've seen the slides. And maybe you've even seen the leaked rough cut that circulated online. So here it is at last: "Anonymity and Identity Online (Taylor's Version)" https://t.co/bJ6v2rnhKQ

Last day to apply! Please join us on Sat, Aug 5, 2023 from 11:30AM - 1PM ET for the @AOM_STR Junior Faculty Paper Development Workshop in Boston! We have a fabulous lineup of mentors who have generously agreed to share feedback and advice. See the instructions below to submit.

Check out this cool paper (JPE R&R), on a simple method outperforming differences-in-differences with shorter confidence intervals, and being robust to parallel trend violations, with an R package. Paper: https://t.co/BaSiNqUjC3 Code:

(#4) I thank Prof. Raffaele Conti for guiding me through my first publication. I'm also grateful for all the comments offered by the two anonymous reviewers and other colleagues/scholars.

(#3) As Prof @AlbertoGalasso advised us in EVIS (now #REGIS) seminar (organized by Prof.@gderasse), this is like the classic microeconomic issue of whether lightbulbs becoming brighter increases or reduces sales of lightbulbs.

(#2) We show that stronger patent law affects patenting for strategic purposes in two ways. As each inframarginal patent becomes more effective, the firm needs fewer patents. As the marginal cost of patent protection becomes cheaper, the firm might procure more patents.

(#1) My co-author, Prof. Ivan Png and I are so happy to share that our paper, "When stronger patent law reduces patenting: Empirical evidence" (SMJ forthcoming) is now accessible online ( https://t.co/mULP8hJrMJ).

Congratulations to the Organization Science Dissertation Proposal Competition finalists! Reporting from @INFORMS @OrganizationSci, where finalists will present their work. More about these excellent dissertations in the thread…