Justin Frake

@ChazNuttycombe politicsatwork.org

My day has been immeasurably ruined; the VR scores showing modeled partisanship by job sector is apparently no longer up. vrscores.org/data-visualiza… I was hoping to use it to talk about the shutdown. Original paper: papers.ssrn.com/sol3/papers.cf…

Wow. This is wild. Researchers from Columbia, Michigan, and Maryland released VRscores. VRscores is a dataset linking voter registrations to online worker profiles that allow you to measure the partisan leanings of U.S. employers. 24.5M workers. 500k employers. 2012–2024.

This project was a multi-year collaboration with @ReubenHurst2 and @JustinFrake. To read more about this measurement and how we created it, you can check out our website here: politicsatwork.org And read about how the data were constructed here: papers.ssrn.com/sol3/papers.cf…

Finally, our paper on the pervasiveness of corporate fraud is in print. It has a simple, but important, result: On average 10% of large publicly traded firms commit a relevant fraud every year, costing equityholders $830 billion a year. rdcu.be/c2RhV

@Akshina4 @MichiganRoss Welcome!

1/2: I am very excited to announce that I have officially accepted an offer from @MichiganRoss (Ross School of Business, University of Michigan - Ann Arbor) for the position of Assistant Professor in Marketing.

🚨New @Stata package alert🚨 I have finished a complete overhaul of the 𝗽𝗹𝗼𝘁 suite of ultra-fast graphing commands for large datasets! Updated commands: ✅ use simplified syntax ✅ are downloadable from SSC ✅ come with detailed help files ✅ allow for finer customization

@v_m_bennett Section 3.2.3 (“Bad Controls”) of Mostly Harmless Econometrics takes a potential outcomes approach.

Real footage of applied economists looking for the right level to cluster their standard errors twitter.com/justinehouyaux…

Are you considering a PhD? IDDEAS@MITSloan (Introduction to Diversity in Doctoral Education and Scholarship) is a 2 day (Oct 6-7), aimed at introducing a diverse group of outstanding undergraduates to business research and academia mitsloan.mit.edu/programs/phd/i… Apps due 9/1

In most econ applications, clustering std errors is a problem of design, not sampling. What does that mean? Clustering is needed if treatment assignment is correlated within clusters, not because some clusters were sampled and others were not. 1/8 @jmwooldridge

If you are a data person with strong analytic skills, please consider applying to work with me and my colleagues to help us analyze data from one of the largest and most comprehensive guaranteed income RCTs in the US! jobs.lever.co/ycr/1b74dd3a-3…

@bernardforgues Or this one in R github.com/AakaashRao/sta…

@bernardforgues It’s actually really easy if you use this package in Stata github.com/martin-andrese…

@bernardforgues @derekjharmon Thanks for reading! And thanks for the shoutout!

Don't miss the last @SIEworkshop seminar for this term on Dec 2nd!! @JustinFrake will focus on the intergeneration transmission of organizational misconduct. @LamarPierce1 will be the discussant. Register here: esade.zoom.us/meeting/regist…

1/ Our next @SIEworkshop is on Dec 2 @ 5.30PM (Paris time) @JustinFrake @MichiganRoss presents "Intergeneration Transmission of Organizational Misconduct: Evidence from the Chicago Police Department" Discussant: @LamarPierce1 @WUSTLbusiness Register: esade.zoom.us/meeting/regist…

Learn about studying strategy @MichiganRoss and working with faculty @JustinFrake @derekjharmon @ProfChrisRider Strategy PhD Program Virtual Info Session 11/9/21 at 11am-1230pm! Register: tinyurl.com/RSB-StrategyPh…

@kylefbutts Thank you! This is great. Can I ask how standard errors estimated? Are they just HW robust?

🎁New gift alert:🎁 The entire diff-in-diff robustness check in one R function: kylebutts.com/did2s/referenc… Beta mode, so please report any bugs if you try it!!

@jondr44 SwitchResX worked for me (along with a good USB—C to HDMI converter madrau.com

Is there any good solution for getting a Macbook to display well on a large non-Apple monitor (Dell 34" Ultrawide)? My options appear to be tiny text or decreasing the resolution and making everything blurry. Everything worked fine on my PC by setting zoom to 200%.