The Mixtape with Scott

What a pleasure it is this week to introduce my guest on the Mixtape with Scott, Dr. Pedro Sant’Anna. Had you asked me a few years ago the likelihood I’d make such a good new friend this late in life, I would not have guessed it, but from countless conversations on social media, and even more in DM on our Slack channel with two other close friends, Pedro Sant’Anna has become one of my favorite people in life. A constantly upbeat, friendly, energetic man, patient to a fault to explain every single detail of econometrics, and enjoying himself as does so, he is one of the best in the profession. He is as many of you know one of the half dozen important young econometricians that have made major contributions to the difference-in-differences research design. His productivity is intense so I can’t name them all, but the two I know best, almost by heart, are:* Callaway and Sant’Anna (2021), “Difference-in-differences with multiple time periods” Journal of Econometrics* Sant’Anna and Zhou (2020), “Doubly-robust difference-in-differences estimators”, Journal of EconometricsThe first one has over 2000 cites and it was only published a little over a year ago. He also has an Econometrica with Jon Roth on issues related to functional form and parallel trends in diff-in-diff and a review article (also with Jon Roth, but also with John Poe and Alyssa Bilinski) for anyone who wants to in one stop learn everything you need to know about diff-in-diff. In this mixtape episode, though, we learn more than just his papers. Pedro shares his story with me. I hope you like it and I hope as always you come to value both his story, but also the contemporary ongoing series I’m doing on the many stories of economists. Because to quote, Sue Johnson:“We use stories to make sense of our lives. And we use stories as models to guide us in the future. We shape stories, and then stories shape us.”Consider subscribing, sharing and possibly even supporting the substack as I continue to try and accumulate enough stories of living economists that we have those stories to help us make sense of our lives, but also an oral history of the profession. Thank you again for your support! Youtube below!Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Mixtape Substack at causalinf.substack.com/subscribe

This week’s episode of the Mixtape with Scott is a little out of order. Season two’s episodes are going to be a little out of order, based on what feels like the best next episode to present at that time. So I decided after doing my interview with University of Arizona professor of economics, Hide Ichimura, that I wanted to release it because I had such a delightful time talking with him. Dr. Ichimura is an econometrician whose work I’ve gotten to know more recently because it’s been experiencing a little bit of a revival (though it’s always remained very popular over the years) within the difference-in-differences literature thanks, in part, to the Sant’anna and Zhao (2020) Journal of Econometrics on robust diff-in-diff, Callaway and Sant’anna (2021) paper on differential timing, and in many ways, other papers that conduct certain kinds of imputations and estimations that are similar in spirit like Borusyak, et al’s (2022) robust efficient imputation estimator, and even Abadie and Imbens (2011) selection bias adjustment method if you squint your eyes. I had a wonderful experience talking with Dr. Ichimura today. This is sort of part of my broader interest, as I say in the intro, in interviewing econometricians who were active in the 1990s working on topics in causal inference, and to that end, I had in mine two Restuds by Dr. Ichimura with Heckman and Todd (1997) and a 1998 one in Restud also by Heckman and Todd (and the identical title!!), both on program evaluation. But I also just in general wanted to hear his story, and I’m so glad I did and that he would share it. At the end of the episode, I asked him to share with me a paper that, maybe isn’t his favorite, but that has always stuck in his mind. He shared with me Stephen Nickell’s 1979 article in Econometrica entitled “Estimating the Probability of Leaving Unemployment”. As always, opening introduction music is by Wes Cunningham (no relation).And don’t forget to subscribe, share and maybe even support this! This podcast is subsidized by your donations and my workshops! Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Mixtape Substack at causalinf.substack.com/subscribe

In this week’s interview on the Mixtape with Scott, I had the pleasure of interviewing Clair Brown, a labor economist at the University of California - Berkeley. Dr. Brown’s career has spanned several topics like discrimination, industrial economics, and climate. Dr. Brown’s late career has made several turns into environmental economics, particularly climate, but also a re-envisioning of the field of economics with her book Buddhist Economics. Dr. Brown’s work has always focused on issues around welfare that are often massaged out of her models, like meaning, community and fairness in labor markets. I thoroughly enjoyed our time together, and I hope you find it interesting too. Please remember to subscribe and share!Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Mixtape Substack at causalinf.substack.com/subscribe

Time for a new podcast episode! In this week’s episode, I have the pleasure of sitting down with Dr. Beatrice Cherrier, a widely recognized expert in the history of economic thought, and one of my personal favorite economists around. Beatrice is an associate professor of economics at the Center for Research in Economics and Statistics in France. She is a font of wisdom and insight about more parts of the field of economics than is found in most people who specialize in even one of those areas. But she is also a very endearing person and a pleasure to talk to, and I hope you enjoy this interview. Please remember to share and subscribe! Get full access to Scott's Mixtape Substack at causalinf.substack.com/subscribe

In this episode, Scott interviews Dan Hamermesh, a professor emeritus and labor economist. They discuss Dan's career, his experiences studying under H. Greg Lewis, and the evolution of labor economics. They also talk about Dan's childhood in suburban Chicago, his interest in numbers and statistics, and his experiences in the job market. The speakers delve into the concept of labor supply and voluntary uncompensated labor, questioning motives behind such activities.

Season two of the Mixtape with Scott is up and boy do I have a dynamite first guest. None other than the man himself, Dr. Jeffrey Wooldridge! Jeff, as I say in the opening, is the author of two phenomenally popular books (here, here and here’s the solutions) in econometrics that has raised an entire generation of economists. We have a great conversation about his life and career and I hope you enjoy it!Expect new episodes every Tuesday morning. Thanks to my good friend, Wes Cunningham (no relation), for the amazing opener music he made for me — it’s perfect. And thanks to Arslan Yaqoob who set the music to the awesome montage of last season’s guests and has been producing them for me this entire time. Check out the YouTube video below if you enjoy watching more than listening. Get full access to Scott's Mixtape Substack at causalinf.substack.com/subscribe

Phillip Levine, a labor economist, discusses his career, research on sex and abortion, experiences at Princeton University, and new work on education in an entertaining interview. He shares personal insights about his upbringing and the impact of economic hardships on his family. The podcast covers topics such as the decline of economic development in Syracuse, childhood aspirations, choosing a college, preparing for graduate school, the impact of a labor economist's papers, the influence of shows like Sesame Street on early childhood education, and making college pricing more transparent.

Chris Nosko is a PhD economist. He did his PhD in economics at Harvard in the mid 2010s before going to Chicago Booth take a job as an assistant professor. But for a year prior to taking that job, between Harvard and Chicago, he did a postdoc fellowship at eBay where he, Thomas Blake and Steve Tadelis met and worked together on a project involved a serendipitous event at the company in which eBay quit paying for branded key words (e.g., “eBay Volvo decals”, “eBay typewriters”) on some but not all search engine auctions. They asked for the data on traffic to the site before and after eBay quit paying for branded keywords for all search engines (both those they kept paying and those they didn’t), ran a simple event study diff-in-diff and found evidence that search engine marketing at eBay was perhaps not causing increased traffic to the site. They convinced management to field a large RCT which confirmed their diff-in-diff results, and that study was published in Econometrica. Not a shabby way to start a career as an economist. For many of us, a PhD in economics from Harvard, a successful partnership with eBay resulting in a study destined for a Top 5 and a tenure track job at Chicago Booth meant staying at Booth and having a career as an academic. No one outrightly says that the only meaningful life you can have as an economist is to be an academic, as it’s vulgar, opinionated and obviously false to talk that way about how someone else should live their life, but the norms are pretty powerful nonetheless. Well, starting around the time that Chris got his job at Booth, tech began experiencing a surge in hiring of PhD economists, largely driven by Amazon’s nearly insatiable appetite for them. Talking with people at Amazon, I have learned that behind this push was Pat Bajari, and behind Pat Bajari was Jeff Bezos who had long believed economics, and economists more specifically, had unique value. As Susan Athey said to me, though, in an interview earlier, Bajari though had to do pull a rabbit out of a hat. Whereas the first wave of economists to tech — people like Hal Varian, Susan Athey, Preston McAfee — had largely been micro theorists helping craft the foundations of a business model through auctions and advertising that would support search engines, arguably the core arteries of the internet itself — Bajari would have the task of bringing in young people, fresh out of grad school, and in Athey’s words, make them productive. And one of the people Bajari would ultimately tap do that was Chris Nosko, an assistant professor at Chicago Booth and someone trained in structural industrial organization, one of the economics’ more interesting experiments of fusing deep microeconomic theory with econometric estimation. Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.Nosko was a Ariel Pakes student at Harvard and was well versed in so many different parts of economics and modern technology that it almost seems predestined that he would ultimately leave Chicago Booth permanently and go to Amazon when Bajari finally convinced him to, but that’s all selection on the dependent variable reasoning. When we look back in time at decisions we made, our mind tends to forget that there was a moment when we could’ve gone left instead of right. The same with Chris — there was a decision that had to be made to leave a career as an academic. The decision materialized into what it materialized, but to pretend it was easy, or that it didn’t have risk, or that Chris didn’t try to manage that risk in some ways is really unfair to our earlier selves or even our future selves who are in situations facing, not probabilistic risk but more like Knightian uncertainty in which no one truly has a clue what possibly could happen. But Chris did leave. Sort of. He took “a leave of absence” from Booth in 2015 and took a job at Amazon, then permanently left Booth in 2016. He spent four years at Amazon before leaving for Uber, one of the more impressive firms to ever exist for creating an actual open marketplace solving two sided matching problems through algorithms and prices. Algorithms, prices and rules — three ways, no doubt there are others, in which modern economies coordinate productive activity. Is it really so surprising that economics might be valued by tech firms given the complex coordination they try to solve using all three?Thank you for reading Scott's Substack. This post is public so feel free to share it.Chris has been at Uber for four years. He is now Vice President and Head of Science and Analytics for Uber Product there.  Within tech, economists sort into tons of different jobs with titles that to an academic don’t make a ton of sense — just like so much of what academics’ lives takes place within administrative units that make little sense to anyone else. If Chris isn’t the chief economist, though, at Uber, I figure he’s probably up there. And he’s my guest this week on The Mixtape with Scott as part of my longer, unfolding series I call “Economists in tech”. Our conversation covered a lot of ground. We talked about growing up in rural Oregon, falling into programming early on and working a few years between high school and college during the early wave tech boom of the late 1990s and early 2000s as a programmer. It wasn’t exactly what he would do later, as that was more web design and less machine learning and statistics, but the aptitude of programming is very portable and his deep knowledge of tech sectors was anyway established or at least re-invested in while there. We talked about his love for his liberal arts education at the University of Chicago where he did his undergraduate degree, and his broad navigation of economics as a field and a career.  All in all, it was a fun opportunity to talk to Chris, to learn more about his own path, about the world out there outside of academia, what economists do in tech, and how all of these things fit together for both economics but maybe more importantly just for Chris himself. I think a lot of people are going to find Chris’s story very interesting and personally intriguing as they may see him in themselves. You can read some of Chris’s work here. Thanks again for tuning in! I hope you enjoy this week’s interview as much as I did! If you are enjoying these, please consider supporting me by sharing the podcast and/or becoming a paying subscriber!Scott's Substack is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber. Get full access to Scott's Mixtape Substack at causalinf.substack.com/subscribe

** THE EARLIER PODCAST WAS MISSING TEN MINUTES SO I HAD TO REPOST **Brigham Frandsen is a professor at BYU’s economics program. He did his undergrad at BYU double majoring in physics and economics where he coauthored two articles — one in physics on lasers, one on the distribution of income with his professor, the famed James McDonald. In this interview, we discuss a lot of things about his life, BYU’s own production function at producing future economists through careful and intensive mentoring of undergraduates, his time at MIT where he worked with Josh Angrist, and his own research as a labor economist and applied econometrician. I found this to be a really enjoyable talk as I learned more about topics I really wasn’t expecting to learn about. I think one of the themes I see emerging in econometrics over the last few decades that is now becoming a little more salient to me as time passes is the issue of heterogenous treatment effects. Heterogenous treatment effects for instance is at the core of the local average treatment effect literature that Angrist and Imbens were involved in (as well as others at the time). You see it too in the problems with twoway fixed effects and difference-in-differences with staggered adoption. And it’s in Brigham’s work too — from his earliest paper with James McDonald on income distribution, to his newer work with Lars Lefgren on bounds. I think when the story is written, we will see that this heterogeneity and selection have been focal points for econometricians and applied researchers and Brigham will be one of many people I think who helped pushed that forward.If you want to learn more from Brigham, you can though — he’s teaching a workshop on machine learning and causal inference at Mixtape Sessions Oct 27-28. You’ll get to pick up some python probably while you’re at it — a twofer!Thanks for tuning in for the podcast. Apologies for the double posting on this — apparently my software refused to convert the MP4 video to more than 45 minutes no matter what I did. But I have a new workflow and it won’t happen again. Get full access to Scott's Mixtape Substack at causalinf.substack.com/subscribe

Background stuff about causal inference Josh Angrist once quipped (on my podcast!) that a paper he wishes he had written was written by his classmate, Bob LaLonde. It was LaLonde’s job market paper, later published in the AER, that arguably helped bring to broader attention some of the empirical problems around causal inference within applied labor at the time. It was very ingenious too. LaLonde took a job trainings program conducted as an RCT, showed that the causal effect of the program was around $800-900, then dropped the experimental control group. He then pulled in six datasets from nationally representative surveys of Americans (3 from Current Population Survey, 3 from Panel Survey Income Dynamics). He reran the analysis with and without covariates adjustment. Not surprising to modern readers, the estimates were severely biased. Not only were the magnitudes off, most of the time the results showed a negative result. This is noteworthy mainly because of the RCT because the RCT established the ground truth of the trainings program — the truth was the program caused an average return of $800-900. So if using typical methods couldn’t even get close to that — well, that’s a problem. And they didn’t, and one more spark of many sparks that lit the fuse that became the credibility revolution occurred. LaLonde’s paper was published in 1986. Angrist would graduate in 1989 and take a job at Harvard where he’d meet Guido Imbens. During the time together at Harvard in the 1990s, Imbens and Angrist would meet with Don Rubin, the head of the stats department, and between the three of them, several breakthrough contributions to instrumental variables were born. Rajeev Dehejia Revisits LalondeIn the midst of this time were Angrist, Imbens and Rubin were all at Harvard, there was a young graduate student in the economics department named Rajeev Dehejia. Rubin and Imbens one semester co taught an innovative new class on causal inference and Rajeev was one of the students who took it that year. Together with his classmate, Sadek Wahba, the two students decided after the class concluded to not so much replicate Lalonde, but rather extend the analysis using the more up-to-date methods learned from Imbens and Rubin. They chose the propensity score and published two papers reevaluating the Lalonde data — one in 1999 JASA and one in 2002 Restat. The propensity score analysis ultimately did much better than what Lalonde’s analysis had done. A lot of gains were made simply from recognizing the serious common support violations rampant in all six of those datasets. One value of the propensity score is, after all, the dimension reduction you get from taking for instance 10 variables and collapsing into one scalar (the propensity score). Once they did, they saw how bad the negative selection was. A huge number of people on the non experimental controls had propensity scores with so many zeroes after the decimal it was like the data was saying “these people in the CPS wouldn’t appear in that treatment group in a million years!”That’s how I knew of Dehejia for years — the author of two papers showing that propensity score analysis might have promise for program evaluation with deep negative selection baked into the data. I saw him as one of the earliest researchers in the broader credibility revolution trained by that next wave of people connected to Princeton Industrial Relations Section like Angrist as well as Imbens and Rubin who began reshaping our applied practices in paper after paper. So it is a great pleasure to introduce him to you this week in my podcast The Mixtape with Scott. Get full access to Scott's Mixtape Substack at causalinf.substack.com/subscribe