[Script Info] Title: [Events] Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text Dialogue: 0,0:00:00.00,0:00:02.55,Default,,0000,0000,0000,,♪ [music] ♪ Dialogue: 0,0:00:03.80,0:00:05.80,Default,,0000,0000,0000,,- [Narrator] Welcome to \NNobel Conversations. Dialogue: 0,0:00:07.10,0:00:08.10,Default,,0000,0000,0000,,In this episode, Dialogue: 0,0:00:08.10,0:00:11.57,Default,,0000,0000,0000,,Josh Angrist and Guido Imbens\Nsit down with Isaiah Andrews Dialogue: 0,0:00:11.57,0:00:14.60,Default,,0000,0000,0000,,to discuss how the field \Nof econometrics is evolving. Dialogue: 0,0:00:16.10,0:00:18.75,Default,,0000,0000,0000,,- [Isaiah] So Guido and Josh, \Nyou're both pioneers Dialogue: 0,0:00:18.75,0:00:21.50,Default,,0000,0000,0000,,in developing tools for\Nempirical research in economics. Dialogue: 0,0:00:21.50,0:00:22.93,Default,,0000,0000,0000,,And so I'd like to explore Dialogue: 0,0:00:22.93,0:00:25.30,Default,,0000,0000,0000,,sort of where you feel like \Nthe field is heading, Dialogue: 0,0:00:25.30,0:00:28.08,Default,,0000,0000,0000,,sort of economics, econometrics,\Nthe whole thing. Dialogue: 0,0:00:28.51,0:00:31.29,Default,,0000,0000,0000,,To start, I'd be interested to hear Dialogue: 0,0:00:32.20,0:00:35.20,Default,,0000,0000,0000,,about whether you feel like\Nsort of the way in which Dialogue: 0,0:00:35.20,0:00:38.51,Default,,0000,0000,0000,,the local average treatment \Neffects framework sort of took hold Dialogue: 0,0:00:38.80,0:00:42.10,Default,,0000,0000,0000,,has any lessons for how \Nnew empirical methods in economics Dialogue: 0,0:00:42.10,0:00:44.30,Default,,0000,0000,0000,,develop and spread\Nor how they should. Dialogue: 0,0:00:44.56,0:00:45.96,Default,,0000,0000,0000,,- [Josh] That's a good question. Dialogue: 0,0:00:46.61,0:00:47.79,Default,,0000,0000,0000,,You go first. Dialogue: 0,0:00:47.79,0:00:49.46,Default,,0000,0000,0000,,(laughter) Dialogue: 0,0:00:49.70,0:00:53.18,Default,,0000,0000,0000,,Yeah, so I think \Nthe important thing Dialogue: 0,0:00:53.18,0:00:58.55,Default,,0000,0000,0000,,is to come up \Nwith good convincing cases Dialogue: 0,0:00:58.55,0:01:02.21,Default,,0000,0000,0000,,where the questions are clear Dialogue: 0,0:01:02.40,0:01:05.72,Default,,0000,0000,0000,,and where kind of the methods\Napply in general. Dialogue: 0,0:01:05.72,0:01:07.56,Default,,0000,0000,0000,,So one thing I-- Dialogue: 0,0:01:08.07,0:01:12.00,Default,,0000,0000,0000,,Kind of looking back\Nat the subsequent literature, Dialogue: 0,0:01:12.20,0:01:16.70,Default,,0000,0000,0000,,so I really like the regression\Ndiscontinuity literature Dialogue: 0,0:01:16.70,0:01:19.67,Default,,0000,0000,0000,,[where there were] clearly a bunch\Nof really convincing examples Dialogue: 0,0:01:19.67,0:01:21.32,Default,,0000,0000,0000,,and that allowed people to kind of Dialogue: 0,0:01:22.30,0:01:27.20,Default,,0000,0000,0000,,think more clearly, look harder at\Nthe methodological questions. Dialogue: 0,0:01:27.40,0:01:28.80,Default,,0000,0000,0000,,Kind of do clear applications Dialogue: 0,0:01:28.80,0:01:30.60,Default,,0000,0000,0000,,that then allow you \Nto kind of think about, Dialogue: 0,0:01:30.60,0:01:33.60,Default,,0000,0000,0000,,"Wow, do this type of assumption\Nseem reasonable here? Dialogue: 0,0:01:33.60,0:01:38.00,Default,,0000,0000,0000,,What kind of things do we not like\Nin the early papers? Dialogue: 0,0:01:38.50,0:01:39.80,Default,,0000,0000,0000,,How can we improve things?" Dialogue: 0,0:01:39.80,0:01:42.30,Default,,0000,0000,0000,,So having clear applications\Nmotivating, Dialogue: 0,0:01:43.40,0:01:46.40,Default,,0000,0000,0000,,these literatures, \NI think it's very helpful. Dialogue: 0,0:01:46.80,0:01:49.30,Default,,0000,0000,0000,,I'm glad you mentioned\Nthe regression discontinuity, Guido. Dialogue: 0,0:01:49.30,0:01:53.30,Default,,0000,0000,0000,,I think there's a lot of \Ncomplementarity between IV and RD, Dialogue: 0,0:01:54.70,0:01:57.06,Default,,0000,0000,0000,,Instrumental Variables and\NRegression Discontinuity. Dialogue: 0,0:02:00.35,0:02:03.26,Default,,0000,0000,0000,,And a lot of \Nthe econometric applications Dialogue: 0,0:02:03.26,0:02:04.52,Default,,0000,0000,0000,,of regression discontinuity Dialogue: 0,0:02:04.52,0:02:07.23,Default,,0000,0000,0000,,are what used to be called \N"fuzzy" RD, Dialogue: 0,0:02:07.23,0:02:11.62,Default,,0000,0000,0000,,where, you know, it's not discrete \Nor deterministic at the cutoff, Dialogue: 0,0:02:11.62,0:02:14.90,Default,,0000,0000,0000,,but just the change\Nin rates or intensity. Dialogue: 0,0:02:14.90,0:02:18.74,Default,,0000,0000,0000,,And and the late framework helps us\Nunderstand those applications Dialogue: 0,0:02:18.74,0:02:21.14,Default,,0000,0000,0000,,and gives us a clear interpretation Dialogue: 0,0:02:21.14,0:02:25.00,Default,,0000,0000,0000,,for say, something like, \Nin my paper with Victor Lavy, Dialogue: 0,0:02:25.00,0:02:28.10,Default,,0000,0000,0000,,where we use Maimonides'\Nrule, the class size cutoffs. Dialogue: 0,0:02:28.60,0:02:30.20,Default,,0000,0000,0000,,What are you getting there? Dialogue: 0,0:02:30.40,0:02:31.97,Default,,0000,0000,0000,,Of course, you can\Nanswer that question Dialogue: 0,0:02:31.97,0:02:33.90,Default,,0000,0000,0000,,with a linear \Nconstant effects model, Dialogue: 0,0:02:34.20,0:02:36.31,Default,,0000,0000,0000,,but it turns out \Nwe're not limited to that, Dialogue: 0,0:02:36.31,0:02:39.89,Default,,0000,0000,0000,,and an RD is still very powerful \Nand illuminating, Dialogue: 0,0:02:40.63,0:02:42.10,Default,,0000,0000,0000,,even when, you know, Dialogue: 0,0:02:42.10,0:02:46.00,Default,,0000,0000,0000,,the correlation between the cutoff\Nand the variable of interest, Dialogue: 0,0:02:46.00,0:02:48.98,Default,,0000,0000,0000,,in this case class size, \Nis partial, Dialogue: 0,0:02:48.98,0:02:51.00,Default,,0000,0000,0000,,maybe even not that strong. Dialogue: 0,0:02:52.00,0:02:54.100,Default,,0000,0000,0000,,So there was definitely a kind of,\Na parallel development. Dialogue: 0,0:02:54.100,0:02:56.40,Default,,0000,0000,0000,,It's also interesting, Dialogue: 0,0:02:56.60,0:02:59.78,Default,,0000,0000,0000,,you know, nobody talked about\Nregression discontinuity designs Dialogue: 0,0:02:59.78,0:03:01.22,Default,,0000,0000,0000,,when we were in graduate school, Dialogue: 0,0:03:01.22,0:03:05.30,Default,,0000,0000,0000,,it was something that other social\Nscientists were interested in, Dialogue: 0,0:03:05.80,0:03:09.51,Default,,0000,0000,0000,,and that kind of grew up \Nalongside the late framework Dialogue: 0,0:03:09.51,0:03:14.79,Default,,0000,0000,0000,,and we've both done work on \Nboth applications and methods there Dialogue: 0,0:03:14.79,0:03:18.38,Default,,0000,0000,0000,,and it's been very exciting \Nto see that kind of develop Dialogue: 0,0:03:18.38,0:03:19.80,Default,,0000,0000,0000,,and become so important. Dialogue: 0,0:03:20.00,0:03:23.70,Default,,0000,0000,0000,,It's part of a general evolution,\NI think, towards, you know, Dialogue: 0,0:03:24.00,0:03:27.70,Default,,0000,0000,0000,,credible identification strategies\Ncausal effects... Dialogue: 0,0:03:28.63,0:03:30.20,Default,,0000,0000,0000,,less, you know, making econometrics Dialogue: 0,0:03:30.40,0:03:33.30,Default,,0000,0000,0000,,more about causal questions\Nthan about models. Dialogue: 0,0:03:33.64,0:03:34.65,Default,,0000,0000,0000,,In terms of the future, Dialogue: 0,0:03:34.65,0:03:37.86,Default,,0000,0000,0000,,I think one thing that LATE \Nhas helped facilitate Dialogue: 0,0:03:37.86,0:03:42.70,Default,,0000,0000,0000,,is a move towards more creative,\Nrandomized trials, where, Dialogue: 0,0:03:42.70,0:03:44.40,Default,,0000,0000,0000,,you know, there's\Nsomething of interest, Dialogue: 0,0:03:45.50,0:03:50.70,Default,,0000,0000,0000,,it's not possible or straightforward\Nto simply turn it off or on, Dialogue: 0,0:03:51.00,0:03:54.58,Default,,0000,0000,0000,,but you can encourage it \Nor discourage it. Dialogue: 0,0:03:54.58,0:03:58.20,Default,,0000,0000,0000,,So you subsidize schooling \Nwith financial aid, for example. Dialogue: 0,0:03:59.00,0:04:02.08,Default,,0000,0000,0000,,So now we have a whole \Nframework for interpreting that, Dialogue: 0,0:04:03.60,0:04:06.90,Default,,0000,0000,0000,,and it kind of opens\Nthe doors to randomized trials Dialogue: 0,0:04:06.90,0:04:10.30,Default,,0000,0000,0000,,of things that that maybe would,\Nyou know, Dialogue: 0,0:04:10.30,0:04:12.47,Default,,0000,0000,0000,,not have seem possible before. Dialogue: 0,0:04:14.50,0:04:17.70,Default,,0000,0000,0000,,We've used that a lot in the work\Nwe do on schools in our-- Dialogue: 0,0:04:17.70,0:04:21.16,Default,,0000,0000,0000,,in the Blueprint Lab at MIT, Dialogue: 0,0:04:22.36,0:04:26.60,Default,,0000,0000,0000,,we're exploiting random assignment\Nand in very creative ways, I think. Dialogue: 0,0:04:28.10,0:04:32.30,Default,,0000,0000,0000,,- [Isaiah] Related to that, do you \Nsee sort of particular factors Dialogue: 0,0:04:32.40,0:04:34.30,Default,,0000,0000,0000,,that make for useful research\Nin econometrics? Dialogue: 0,0:04:34.40,0:04:38.29,Default,,0000,0000,0000,,You've alluded to it \Nhaving a clear connection Dialogue: 0,0:04:38.29,0:04:40.30,Default,,0000,0000,0000,,to problems \Nthat are actually coming up Dialogue: 0,0:04:40.30,0:04:42.65,Default,,0000,0000,0000,,and empirical practice \Nis often a good idea. Dialogue: 0,0:04:43.29,0:04:45.00,Default,,0000,0000,0000,,- [Josh] Isn't it always \Na good idea? Dialogue: 0,0:04:45.70,0:04:50.10,Default,,0000,0000,0000,,I often find myself sitting in an\Neconometrics theory seminar, Dialogue: 0,0:04:50.70,0:04:52.50,Default,,0000,0000,0000,,say the Harvard MIT seminar, Dialogue: 0,0:04:53.40,0:04:55.94,Default,,0000,0000,0000,,and I'm thinking, "What problem\Nis this guy solving? Dialogue: 0,0:04:55.94,0:04:57.96,Default,,0000,0000,0000,,Who has this problem?" Dialogue: 0,0:04:57.96,0:04:59.80,Default,,0000,0000,0000,,And, you know, Dialogue: 0,0:05:01.60,0:05:04.70,Default,,0000,0000,0000,,sometimes there's an\Nembarrassing silence if I ask Dialogue: 0,0:05:04.90,0:05:08.30,Default,,0000,0000,0000,,or there might be\Na fairly contrived scenario. Dialogue: 0,0:05:08.80,0:05:11.60,Default,,0000,0000,0000,,I want to see \Nwhere the tool is useful. Dialogue: 0,0:05:12.50,0:05:14.90,Default,,0000,0000,0000,,There are some \Npurely foundational tools, Dialogue: 0,0:05:14.90,0:05:17.60,Default,,0000,0000,0000,,I do take the point, you know, \Nthere are people who are Dialogue: 0,0:05:18.20,0:05:22.50,Default,,0000,0000,0000,,working on conceptual\Nfoundations of, you know, Dialogue: 0,0:05:22.60,0:05:25.30,Default,,0000,0000,0000,,it's more-- becomes more like\Nmathematical statistics. Dialogue: 0,0:05:25.80,0:05:28.20,Default,,0000,0000,0000,,I mean, I remember \Nan early example of that that I, Dialogue: 0,0:05:28.20,0:05:30.35,Default,,0000,0000,0000,,you know, I struggled to understand Dialogue: 0,0:05:30.35,0:05:32.50,Default,,0000,0000,0000,,was the idea\Nof stochastic equicontinuity, Dialogue: 0,0:05:32.50,0:05:35.07,Default,,0000,0000,0000,,which one of my thesis advisors,\NWhitney Newey, Dialogue: 0,0:05:35.07,0:05:36.90,Default,,0000,0000,0000,,was using to great effect Dialogue: 0,0:05:37.50,0:05:39.90,Default,,0000,0000,0000,,and I was trying to understand that\Nand there isn't really-- Dialogue: 0,0:05:40.60,0:05:45.20,Default,,0000,0000,0000,,It's really foundational, it's not\Nan application that's driving that, Dialogue: 0,0:05:45.89,0:05:47.30,Default,,0000,0000,0000,,at least not immediately Dialogue: 0,0:05:48.60,0:05:53.20,Default,,0000,0000,0000,,but most things are not like that\Nand so there should be a problem. Dialogue: 0,0:05:53.80,0:05:59.10,Default,,0000,0000,0000,,And I think it's on the seller \Nof that sort of thing, Dialogue: 0,0:06:00.10,0:06:02.25,Default,,0000,0000,0000,,you know, because there's \Nopportunity cost, Dialogue: 0,0:06:02.25,0:06:05.17,Default,,0000,0000,0000,,the time and attention,\Nand effort to understand things Dialogue: 0,0:06:05.17,0:06:07.20,Default,,0000,0000,0000,,to, you know, \Nit's on the seller to say, Dialogue: 0,0:06:07.40,0:06:08.90,Default,,0000,0000,0000,,"Hey, I'm solving this problem Dialogue: 0,0:06:09.40,0:06:12.90,Default,,0000,0000,0000,,and here's a set of results\Nthat show that it's useful, Dialogue: 0,0:06:12.90,0:06:15.20,Default,,0000,0000,0000,,and here's some insight\Nthat I get." Dialogue: 0,0:06:16.20,0:06:18.28,Default,,0000,0000,0000,,- [Isaiah] As you said, Josh, great,\Nsort of there's been a move Dialogue: 0,0:06:18.28,0:06:20.70,Default,,0000,0000,0000,,in the direction of thinking \Nmore about causality Dialogue: 0,0:06:20.70,0:06:22.80,Default,,0000,0000,0000,,in economics and empirical\Nwork in economics, Dialogue: 0,0:06:22.90,0:06:24.80,Default,,0000,0000,0000,,any consequences of sort of the-- Dialogue: 0,0:06:24.80,0:06:26.57,Default,,0000,0000,0000,,the spread of that view \Nthat surprised you Dialogue: 0,0:06:26.57,0:06:28.86,Default,,0000,0000,0000,,or anything that you view\Nas downsides Dialogue: 0,0:06:28.86,0:06:31.40,Default,,0000,0000,0000,,of sort of the way \Nthat empirical economics has gone? Dialogue: 0,0:06:31.50,0:06:34.19,Default,,0000,0000,0000,,- [Josh] Sometimes I see, \Nsomebody does IV Dialogue: 0,0:06:34.19,0:06:38.50,Default,,0000,0000,0000,,and they get a result \Nwhich seems implausibly large. Dialogue: 0,0:06:38.80,0:06:40.20,Default,,0000,0000,0000,,That's the usual case. Dialogue: 0,0:06:42.50,0:06:45.22,Default,,0000,0000,0000,,So it might be, you know,\Nan extraordinarily large Dialogue: 0,0:06:45.22,0:06:48.60,Default,,0000,0000,0000,,causal effect of some \Nrelatively minor intervention, Dialogue: 0,0:06:49.10,0:06:52.80,Default,,0000,0000,0000,,which was randomized\Nor for which you could make a case Dialogue: 0,0:06:52.90,0:06:54.90,Default,,0000,0000,0000,,that there's a good design. Dialogue: 0,0:06:54.90,0:06:58.33,Default,,0000,0000,0000,,And then when I see that,\Nand, you know, I think Dialogue: 0,0:06:58.90,0:07:00.46,Default,,0000,0000,0000,,it's very hard for me to believe Dialogue: 0,0:07:00.46,0:07:02.03,Default,,0000,0000,0000,,that this relatively \Nminor intervention Dialogue: 0,0:07:02.03,0:07:04.00,Default,,0000,0000,0000,,has such a large effect. Dialogue: 0,0:07:04.10,0:07:06.11,Default,,0000,0000,0000,,The author will sometimes resort Dialogue: 0,0:07:06.11,0:07:08.69,Default,,0000,0000,0000,,to the local average \Ntreatment effects theorem Dialogue: 0,0:07:08.69,0:07:10.70,Default,,0000,0000,0000,,and say, "Well, these compliers, Dialogue: 0,0:07:10.70,0:07:12.70,Default,,0000,0000,0000,,you know, they're\Nspecial in some way." Dialogue: 0,0:07:13.30,0:07:15.80,Default,,0000,0000,0000,,And, you know, \Nthey just benefit extraordinarily Dialogue: 0,0:07:15.80,0:07:17.60,Default,,0000,0000,0000,,from this intervention. Dialogue: 0,0:07:18.10,0:07:20.90,Default,,0000,0000,0000,,And I'm reluctant \Nto take that at face value. Dialogue: 0,0:07:20.90,0:07:23.75,Default,,0000,0000,0000,,I think, you know,\Noften when effects are too big, Dialogue: 0,0:07:24.30,0:07:26.78,Default,,0000,0000,0000,,it's because the exclusion\Nrestriction is failing, Dialogue: 0,0:07:26.78,0:07:29.24,Default,,0000,0000,0000,,so you don't really have the right\Nendogenous variable Dialogue: 0,0:07:29.24,0:07:31.38,Default,,0000,0000,0000,,to scale that result. Dialogue: 0,0:07:32.00,0:07:35.70,Default,,0000,0000,0000,,And so I'm not too happy to see Dialogue: 0,0:07:35.80,0:07:38.80,Default,,0000,0000,0000,,you know, just sort of\Na generic heterogeneity Dialogue: 0,0:07:38.90,0:07:41.61,Default,,0000,0000,0000,,argument being used \Nto excuse something Dialogue: 0,0:07:41.61,0:07:43.80,Default,,0000,0000,0000,,that I think might be \Na deeper problem. Dialogue: 0,0:07:45.19,0:07:47.36,Default,,0000,0000,0000,,- [Guido] I think it played \Nsomewhat of an unfortunate role Dialogue: 0,0:07:47.36,0:07:49.98,Default,,0000,0000,0000,,when the discussions kind of \Nbetween reduced form Dialogue: 0,0:07:49.98,0:07:51.70,Default,,0000,0000,0000,,and structural approaches, Dialogue: 0,0:07:51.70,0:07:55.51,Default,,0000,0000,0000,,where I feel \Nthat wasn't quite right. Dialogue: 0,0:07:56.09,0:07:58.81,Default,,0000,0000,0000,,The instrumental \Nvariables assumptions Dialogue: 0,0:07:58.81,0:08:03.62,Default,,0000,0000,0000,,are at the core - structural \Nassumptions about behavior - Dialogue: 0,0:08:03.62,0:08:05.20,Default,,0000,0000,0000,,they were coming from economic-- Dialogue: 0,0:08:07.10,0:08:09.90,Default,,0000,0000,0000,,thinking about the economic\Nbehavior of agents, Dialogue: 0,0:08:10.30,0:08:15.00,Default,,0000,0000,0000,,and somehow it got\Npushed in a direction Dialogue: 0,0:08:15.10,0:08:17.60,Default,,0000,0000,0000,,that I think wasn't \Nreally very helpful. Dialogue: 0,0:08:18.80,0:08:21.70,Default,,0000,0000,0000,,The way I think, initially the-- Dialogue: 0,0:08:22.80,0:08:26.48,Default,,0000,0000,0000,,we wrote things up, it was \Ndescribing what was happening, Dialogue: 0,0:08:26.48,0:08:29.49,Default,,0000,0000,0000,,there were a set of methods \Npeople were using, Dialogue: 0,0:08:29.49,0:08:32.11,Default,,0000,0000,0000,,we clarified what \Nthose methods were doing Dialogue: 0,0:08:32.11,0:08:38.48,Default,,0000,0000,0000,,and in a way that I think\Ncontain a fair amount of insight, Dialogue: 0,0:08:39.10,0:08:42.05,Default,,0000,0000,0000,,but it somehow \Nit got pushed into a corner Dialogue: 0,0:08:42.05,0:08:45.00,Default,,0000,0000,0000,,that I don't think \Nwas necessarily very helpful. Dialogue: 0,0:08:45.10,0:08:46.85,Default,,0000,0000,0000,,- [Isaiah] I mean, \Njust the language Dialogue: 0,0:08:46.85,0:08:48.60,Default,,0000,0000,0000,,of reduced form versus structural Dialogue: 0,0:08:48.60,0:08:50.82,Default,,0000,0000,0000,,I find kind of funny \Nin the sense that, Dialogue: 0,0:08:50.82,0:08:53.10,Default,,0000,0000,0000,,right, the local average treatment\Neffect model, right? Dialogue: 0,0:08:53.10,0:08:56.11,Default,,0000,0000,0000,,The potential outcomes model is \Na nonparametric structural model, Dialogue: 0,0:08:56.11,0:08:58.60,Default,,0000,0000,0000,,if you want to think about it, \Nas you sort of suggested, Guido. Dialogue: 0,0:08:58.60,0:09:00.10,Default,,0000,0000,0000,,So, there's something, Dialogue: 0,0:09:00.10,0:09:01.26,Default,,0000,0000,0000,,there's something a little funny Dialogue: 0,0:09:01.26,0:09:03.34,Default,,0000,0000,0000,,about putting these \Ntwo things in oposition when... Dialogue: 0,0:09:03.34,0:09:04.69,Default,,0000,0000,0000,,- [Guido] Yes.\N- [Josh] Well, that language, Dialogue: 0,0:09:04.69,0:09:08.16,Default,,0000,0000,0000,,of course, comes from the 70s \Nequations framework Dialogue: 0,0:09:08.16,0:09:09.52,Default,,0000,0000,0000,,that we inherited. Dialogue: 0,0:09:10.40,0:09:11.53,Default,,0000,0000,0000,,It has the advantage Dialogue: 0,0:09:11.53,0:09:14.16,Default,,0000,0000,0000,,that people seem to know \Nwhat you mean when you use it, Dialogue: 0,0:09:14.16,0:09:16.24,Default,,0000,0000,0000,,but might be that people \Nare hearing different, Dialogue: 0,0:09:16.24,0:09:18.20,Default,,0000,0000,0000,,different people\Nare hearing different things. Dialogue: 0,0:09:18.30,0:09:20.53,Default,,0000,0000,0000,,- [Guido] Yeah. I think [inaudible]\Nhas sort of become-- Dialogue: 0,0:09:20.53,0:09:22.56,Default,,0000,0000,0000,,used in a little bit \Nof the pejorative way, yeah? Dialogue: 0,0:09:22.56,0:09:24.75,Default,,0000,0000,0000,,- [Josh] Sometimes.\N- [Guido] The word. Dialogue: 0,0:09:24.75,0:09:28.25,Default,,0000,0000,0000,,Which is not really quite what \Nit was originally intended for. Dialogue: 0,0:09:30.10,0:09:33.09,Default,,0000,0000,0000,,- [Isaiah] I guess something else\Nthat strikes me in thinking about Dialogue: 0,0:09:33.09,0:09:35.64,Default,,0000,0000,0000,,the effects of the local average\Ntreatment effect framework Dialogue: 0,0:09:35.64,0:09:38.20,Default,,0000,0000,0000,,is that often folks will appeal to Dialogue: 0,0:09:38.20,0:09:41.80,Default,,0000,0000,0000,,a local average treatment effects\Nintuition for settings well beyond Dialogue: 0,0:09:42.00,0:09:43.70,Default,,0000,0000,0000,,ones where any sort \Nof formal results Dialogue: 0,0:09:43.70,0:09:45.44,Default,,0000,0000,0000,,has actually been established. Dialogue: 0,0:09:45.44,0:09:50.19,Default,,0000,0000,0000,,And I'm curious, given all the work\Nthat you guys did to, you know, Dialogue: 0,0:09:50.19,0:09:52.39,Default,,0000,0000,0000,,establish late results \Nin different settings, Dialogue: 0,0:09:52.39,0:09:54.42,Default,,0000,0000,0000,,I'm curious, any thoughts on that? Dialogue: 0,0:09:55.36,0:09:57.42,Default,,0000,0000,0000,,- [Guido] I think there's\Ngoing to be a lot of cases Dialogue: 0,0:09:57.42,0:10:02.20,Default,,0000,0000,0000,,where the intuition \Ndoes get you some distance, Dialogue: 0,0:10:02.80,0:10:05.20,Default,,0000,0000,0000,,but it's going to be \Nsomewhat limited Dialogue: 0,0:10:05.20,0:10:07.60,Default,,0000,0000,0000,,and establishing \Nformal results there Dialogue: 0,0:10:08.40,0:10:09.49,Default,,0000,0000,0000,,may be a little tricky Dialogue: 0,0:10:09.49,0:10:12.70,Default,,0000,0000,0000,,and then maybe only work \Nin special circumstances, Dialogue: 0,0:10:14.60,0:10:16.54,Default,,0000,0000,0000,,and you end up\Nwith a lot of formality Dialogue: 0,0:10:16.54,0:10:19.50,Default,,0000,0000,0000,,that may not quite \Ncapture the intuition. Dialogue: 0,0:10:19.90,0:10:21.55,Default,,0000,0000,0000,,Sometimes I'm somewhat \Nuneasy with them Dialogue: 0,0:10:21.55,0:10:24.44,Default,,0000,0000,0000,,and they are not necessarily\Nthe papers I would want to write, Dialogue: 0,0:10:25.15,0:10:27.22,Default,,0000,0000,0000,,but I do think something-- Dialogue: 0,0:10:27.22,0:10:31.22,Default,,0000,0000,0000,,intuition often does capture \Npart of the problem. Dialogue: 0,0:10:33.10,0:10:36.30,Default,,0000,0000,0000,,I think, in some sense we were\Nkind of very fortunate there Dialogue: 0,0:10:36.90,0:10:40.50,Default,,0000,0000,0000,,in the way that the late paper go handle. It.\NDon't know if that, actually the editor, Dialogue: 0,0:10:40.60,0:10:41.70,Default,,0000,0000,0000,,made it much shorter Dialogue: 0,0:10:42.10,0:10:46.30,Default,,0000,0000,0000,,and that then allowed us to kind of\Nfocus on very clear, crisp results Dialogue: 0,0:10:47.10,0:10:49.80,Default,,0000,0000,0000,,where if, you know, this, Dialogue: 0,0:10:50.00,0:10:54.20,Default,,0000,0000,0000,,this is somewhat unfortunate tendency in\Nthe commercialization of having the papers. Dialogue: 0,0:10:54.60,0:10:58.80,Default,,0000,0000,0000,,Well, you should be able to fix that, man.\NI'm trying to take some time to fix that. Dialogue: 0,0:10:59.40,0:11:02.70,Default,,0000,0000,0000,,I think this is an example where it's sort\Nof very clear that having it. Be sure. Dialogue: 0,0:11:02.90,0:11:08.00,Default,,0000,0000,0000,,It's actually impose that no paper can\Nbe longer than the late paper that wow. Dialogue: 0,0:11:08.80,0:11:14.30,Default,,0000,0000,0000,,Great. At least no Theory. No Theory Pig.\NYeah, and I think, I think they're well, Dialogue: 0,0:11:14.50,0:11:16.80,Default,,0000,0000,0000,,I'm trying very hard to get\Nthe papers to be shorter. Dialogue: 0,0:11:16.80,0:11:18.70,Default,,0000,0000,0000,,And I think there's a lot of value Dialogue: 0,0:11:19.20,0:11:22.60,Default,,0000,0000,0000,,today because it's often the second\Npart of the paper that doesn't actually Dialogue: 0,0:11:23.70,0:11:26.50,Default,,0000,0000,0000,,Get you much further\Nand understanding things Dialogue: 0,0:11:27.00,0:11:31.70,Default,,0000,0000,0000,,but and it does make things much\Nharder to read and, you know, Dialogue: 0,0:11:32.40,0:11:33.70,Default,,0000,0000,0000,,it sort of goes back to Dialogue: 0,0:11:34.20,0:11:38.50,Default,,0000,0000,0000,,how I think he kind of a trick should\Nbe done to you should focus on the see. Dialogue: 0,0:11:38.70,0:11:41.30,Default,,0000,0000,0000,,It should be reasonably\Nclose to empirical problems. Dialogue: 0,0:11:41.50,0:11:43.90,Default,,0000,0000,0000,,They should be very clear problems. Dialogue: 0,0:11:44.80,0:11:48.90,Default,,0000,0000,0000,,But then often the the theory\Ndoesn't need to be quite so long. Dialogue: 0,0:11:49.00,0:11:49.30,Default,,0000,0000,0000,,Yeah, Dialogue: 0,0:11:51.10,0:11:53.40,Default,,0000,0000,0000,,I think they had things have Dialogue: 0,0:11:53.60,0:11:54.70,Default,,0000,0000,0000,,On a little off track. Dialogue: 0,0:11:56.40,0:11:58.40,Default,,0000,0000,0000,,The relatively recent change has been a Dialogue: 0,0:11:58.50,0:12:02.20,Default,,0000,0000,0000,,seeming big increase in demand for\Npeople with sort of econometrics. Dialogue: 0,0:12:02.20,0:12:04.80,Default,,0000,0000,0000,,Causal effect, estimation\Nskills in the tech sector. Dialogue: 0,0:12:05.00,0:12:09.00,Default,,0000,0000,0000,,I'm interested either of you have\Nthoughts on sort of how that's gonna Dialogue: 0,0:12:09.20,0:12:11.60,Default,,0000,0000,0000,,how that's going to interact with\Nthe development of empirical methods, Dialogue: 0,0:12:11.60,0:12:14.30,Default,,0000,0000,0000,,or Empirical research, and\Neconomics. Going forward, sort of Dialogue: 0,0:12:14.60,0:12:21.00,Default,,0000,0000,0000,,whether sort of a meta point, which\Nis there's this new kind of employer Dialogue: 0,0:12:21.80,0:12:26.00,Default,,0000,0000,0000,,the Amazons and the Uber and, you know, Dialogue: 0,0:12:26.20,0:12:27.60,Default,,0000,0000,0000,,Riser world Dialogue: 0,0:12:28.00,0:12:29.30,Default,,0000,0000,0000,,and I think that's great. Dialogue: 0,0:12:29.30,0:12:33.20,Default,,0000,0000,0000,,And I'd like to tell my students about\Nthat, you know, especially at MIT. Dialogue: 0,0:12:33.20,0:12:37.00,Default,,0000,0000,0000,,We have a lot of computer science\NMajors. That's our biggest major Dialogue: 0,0:12:37.40,0:12:42.80,Default,,0000,0000,0000,,and I try to seduce some of those folks\Ninto economics by saying, you know, Dialogue: 0,0:12:43.20,0:12:45.70,Default,,0000,0000,0000,,you can go work for these, Dialogue: 0,0:12:45.80,0:12:48.40,Default,,0000,0000,0000,,you know companies that\Npeople are very keen to Dialogue: 0,0:12:48.70,0:12:50.80,Default,,0000,0000,0000,,work for because the work seems exciting, Dialogue: 0,0:12:52.00,0:12:56.00,Default,,0000,0000,0000,,you know that the skills that you get in\Neconometrics are are as good or better. Dialogue: 0,0:12:56.10,0:13:01.10,Default,,0000,0000,0000,,Better than than any competing discipline\Nhas to offer. So you should at least Dialogue: 0,0:13:01.40,0:13:04.20,Default,,0000,0000,0000,,take some econ, take some\Neconometrics. And some econ. Dialogue: 0,0:13:04.80,0:13:07.00,Default,,0000,0000,0000,,I did a fun project with a uber Dialogue: 0,0:13:07.60,0:13:12.90,Default,,0000,0000,0000,,on labor supply of Uber drivers and was\Nvery, very exciting to be part of that. Dialogue: 0,0:13:13.10,0:13:15.40,Default,,0000,0000,0000,,Plus. I got to drive for Uber for a while Dialogue: 0,0:13:15.90,0:13:20.70,Default,,0000,0000,0000,,and I thought that was fun tonight. I did\Nnot make enough that I was attempted to Dialogue: 0,0:13:21.10,0:13:25.10,Default,,0000,0000,0000,,give up by a mighty job, but\NI enjoyed the experience. Dialogue: 0,0:13:25.30,0:13:26.00,Default,,0000,0000,0000,,I see a Dialogue: 0,0:13:26.20,0:13:30.90,Default,,0000,0000,0000,,Cho challenge to our model\Nof graduate education here, Dialogue: 0,0:13:31.70,0:13:37.40,Default,,0000,0000,0000,,which is if we're trading people\Nto go work at Amazon, you know, Dialogue: 0,0:13:37.90,0:13:42.90,Default,,0000,0000,0000,,it's not clear. Why? You know, we should\Nbe paying graduate stipends for that. Dialogue: 0,0:13:43.20,0:13:45.40,Default,,0000,0000,0000,,Why should the taxpayer effectively Dialogue: 0,0:13:46.10,0:13:51.40,Default,,0000,0000,0000,,be subsidizing? That our graduate education\Nin the u.s. Is generously subsidized? Dialogue: 0,0:13:51.40,0:13:56.00,Default,,0000,0000,0000,,Even in private universities. It's\Nultimately there's a lot of public money. Dialogue: 0,0:13:56.10,0:13:59.30,Default,,0000,0000,0000,,Me there. And I think the\Ntraditional rationale for that is, Dialogue: 0,0:13:59.50,0:14:03.90,Default,,0000,0000,0000,,you know, we were training, Educators and\NScholars, and there's a great externality Dialogue: 0,0:14:04.30,0:14:05.70,Default,,0000,0000,0000,,from the work that we do. Dialogue: 0,0:14:05.70,0:14:09.60,Default,,0000,0000,0000,,It's either the research externality,\Nor a teaching externality. Dialogue: 0,0:14:10.10,0:14:14.60,Default,,0000,0000,0000,,But, you know, if many of our students\Nare going to work in the private sector, Dialogue: 0,0:14:16.30,0:14:21.70,Default,,0000,0000,0000,,that's fine, but that maybe their\Nemployers should pay for that. Dialogue: 0,0:14:22.30,0:14:25.10,Default,,0000,0000,0000,,He says, so different from\Npeople working for a Consulting. Dialogue: 0,0:14:26.30,0:14:26.90,Default,,0000,0000,0000,,Trust me. Dialogue: 0,0:14:27.20,0:14:33.00,Default,,0000,0000,0000,,It's not clear to me that the number\Nof jobs in academics has changed. Dialogue: 0,0:14:33.10,0:14:37.60,Default,,0000,0000,0000,,It's just, I feel like this is a\Ngrowing sector whereas Consulting, Dialogue: 0,0:14:37.70,0:14:42.10,Default,,0000,0000,0000,,your right to raise that, it might\Nbe the same for for Consulting. Dialogue: 0,0:14:43.30,0:14:44.40,Default,,0000,0000,0000,,But this, Dialogue: 0,0:14:44.50,0:14:47.50,Default,,0000,0000,0000,,you know, I'm placing more and\Nmore students in these businesses. Dialogue: 0,0:14:47.50,0:14:50.40,Default,,0000,0000,0000,,So, it's on my mind in\Na way that I've sort of, Dialogue: 0,0:14:50.80,0:14:55.50,Default,,0000,0000,0000,,you know, not been attentive to consulting\Njobs, you know, Consulting was always, Dialogue: 0,0:14:55.60,0:15:00.40,Default,,0000,0000,0000,,It's important and I think they'll so\Nthere's some movement from Consulting back Dialogue: 0,0:15:00.40,0:15:02.60,Default,,0000,0000,0000,,into research. It's a little more fluid. Dialogue: 0,0:15:02.90,0:15:03.50,Default,,0000,0000,0000,,The, Dialogue: 0,0:15:03.90,0:15:05.40,Default,,0000,0000,0000,,a lot of the work in the Dialogue: 0,0:15:06.40,0:15:09.80,Default,,0000,0000,0000,,in both domains. I have to say,\Nit's not really different but Dialogue: 0,0:15:10.10,0:15:13.70,Default,,0000,0000,0000,,you know, people who are working\Nin the tech sector are doing things Dialogue: 0,0:15:13.70,0:15:16.80,Default,,0000,0000,0000,,that are potentially of scientific\Ninterest, but mostly it's hidden. Dialogue: 0,0:15:17.10,0:15:20.90,Default,,0000,0000,0000,,Then you really I have to say, you know,\Nwhy, why is the government paying for this? Dialogue: 0,0:15:21.80,0:15:25.50,Default,,0000,0000,0000,,Yeah, although yeah, I mean taquitos point,\NI guess it. There's a, there's a data. Dialogue: 0,0:15:25.60,0:15:30.00,Default,,0000,0000,0000,,Question here of it has the sort\Nof total nanak. It sort of say Dialogue: 0,0:15:30.50,0:15:30.90,Default,,0000,0000,0000,,private Dialogue: 0,0:15:31.30,0:15:34.10,Default,,0000,0000,0000,,for-profit sector employment of econ Ph.D. Dialogue: 0,0:15:34.10,0:15:37.70,Default,,0000,0000,0000,,Program graduates increased or has\Nit just been a substitution from Dialogue: 0,0:15:37.90,0:15:40.20,Default,,0000,0000,0000,,finance and Consulting towards tack. Dialogue: 0,0:15:40.30,0:15:44.30,Default,,0000,0000,0000,,I may be a reaction to something\Nthat's not really happening Dialogue: 0,0:15:44.40,0:15:48.20,Default,,0000,0000,0000,,so bad. I've actually done some work\Nwith some of these tech companies. Dialogue: 0,0:15:49.10,0:15:52.30,Default,,0000,0000,0000,,So I don't disagree with Justice\Npoint that we need to think Dialogue: 0,0:15:52.30,0:15:55.10,Default,,0000,0000,0000,,a little bit about the funding model\Nwhose it was in the end paying for the Dialogue: 0,0:15:55.60,0:15:59.40,Default,,0000,0000,0000,,It education. But from a\Nscientific perspective. Dialogue: 0,0:16:00.10,0:16:03.50,Default,,0000,0000,0000,,The only do these places have\Nhave great data and nowadays. Dialogue: 0,0:16:03.50,0:16:07.10,Default,,0000,0000,0000,,They tend to be very careful\Nwith that for privacy reasons, Dialogue: 0,0:16:07.50,0:16:08.80,Default,,0000,0000,0000,,but also have great questions. Dialogue: 0,0:16:10.20,0:16:11.20,Default,,0000,0000,0000,,I find it very Dialogue: 0,0:16:11.60,0:16:13.30,Default,,0000,0000,0000,,inspiring kind of to listen to Dialogue: 0,0:16:13.30,0:16:15.80,Default,,0000,0000,0000,,the people there and kind of see\Nwhat kind of questions they have Dialogue: 0,0:16:15.90,0:16:17.30,Default,,0000,0000,0000,,and often their questions. Dialogue: 0,0:16:18.20,0:16:20.60,Default,,0000,0000,0000,,That also come up outside of these. Dialogue: 0,0:16:20.70,0:16:25.40,Default,,0000,0000,0000,,These companies have a couple of\Npapers with the rights in the chat. Dialogue: 0,0:16:25.80,0:16:26.30,Default,,0000,0000,0000,,And then Dialogue: 0,0:16:26.50,0:16:31.60,Default,,0000,0000,0000,,as soon as an atheist kind of where we\Nlook at ways of combining experimental data Dialogue: 0,0:16:31.70,0:16:34.10,Default,,0000,0000,0000,,and observational data, and can it there. Dialogue: 0,0:16:35.50,0:16:38.60,Default,,0000,0000,0000,,Rights Chetty was interested\Nin what is the effect Dialogue: 0,0:16:38.70,0:16:44.60,Default,,0000,0000,0000,,of Early Childhood programs on outcomes\Nlater in life? Not just kind of test scores, Dialogue: 0,0:16:44.60,0:16:48.30,Default,,0000,0000,0000,,but on earnings and stuff, and\Nwe cannot be developed methods Dialogue: 0,0:16:48.60,0:16:51.50,Default,,0000,0000,0000,,that would help you shed\Nlight on that, on the some, Dialogue: 0,0:16:52.70,0:16:55.00,Default,,0000,0000,0000,,in some settings and the same problems. Dialogue: 0,0:16:56.30,0:17:00.50,Default,,0000,0000,0000,,Came up kind of in this\Ntech company settings. Dialogue: 0,0:17:00.80,0:17:03.70,Default,,0000,0000,0000,,And so for my perspective, it's Dialogue: 0,0:17:04.40,0:17:07.50,Default,,0000,0000,0000,,the same kind of a stocking two\Npeople doing a protocol work. Dialogue: 0,0:17:07.60,0:17:11.80,Default,,0000,0000,0000,,I tried to kind of look at these\Nspecific problems and then try to come up Dialogue: 0,0:17:11.90,0:17:18.30,Default,,0000,0000,0000,,with more General problems that we\Nformulating the problems at a higher level. Dialogue: 0,0:17:18.50,0:17:22.90,Default,,0000,0000,0000,,So that I can think about solutions\Nthat work in a range of settings. Dialogue: 0,0:17:23.40,0:17:25.50,Default,,0000,0000,0000,,And so from that perspective, the Dialogue: 0,0:17:25.70,0:17:30.30,Default,,0000,0000,0000,,His with the the tech companies I\Njust very valuable and very useful. Dialogue: 0,0:17:30.90,0:17:31.40,Default,,0000,0000,0000,,It's know. Dialogue: 0,0:17:31.70,0:17:33.70,Default,,0000,0000,0000,,We do have students. Now spent Dialogue: 0,0:17:33.80,0:17:37.20,Default,,0000,0000,0000,,doing internships there and\Nthen coming back and writing Dialogue: 0,0:17:37.40,0:17:43.40,Default,,0000,0000,0000,,more interesting thesis, as a\Nresult of their experiences there. Dialogue: 0,0:17:44.60,0:17:47.80,Default,,0000,0000,0000,,If you'd like to watch more\NNobel conversations, click here, Dialogue: 0,0:17:48.20,0:17:50.50,Default,,0000,0000,0000,,or if you'd like to learn\Nmore about econometrics, Dialogue: 0,0:17:50.60,0:17:53.20,Default,,0000,0000,0000,,check out Josh's mastering\Neconometrics series. Dialogue: 0,0:17:53.70,0:17:55.50,Default,,0000,0000,0000,,If you'd like to learn more about he do. Dialogue: 0,0:17:55.60,0:17:58.30,Default,,0000,0000,0000,,Josh and Isaiah check out\Nthe links in the description.