On-line, Chinese production of *The Three-Body Problem*
With subtitles, find it here.
David J. Deming now has a Substack
Forked Lightning, he is from the Harvard Kennedy School, and he is a co-author on the piece with Chetty and John N. Friedman featured on MR earlier today.
In his inaugural post he explains some further results from the paper in more detail:
The second part [of the paper] shows the impact of attending an Ivy-Plus college. Do these colleges actually improve student outcomes, or are they merely cream-skimming by admitting applicants who would succeed no matter where they went to college?[2]
We focus on students who are placed on the waitlist. These students are less qualified than regular admits but more qualified than regular rejects. Crucially, the waitlist admits don’t look any different in terms of admissibility than the waitlist rejects. We verify this by showing that being admitted off the waitlist at one college doesn’t predict admission at other colleges. Intuitively, getting in off the waitlist is about class-balancing and yield management, not overall merit. The college needs an oboe player, or more students from the Mountain West, or whatever. It’s not strictly random, but it’s unrelated to future outcomes (there are a lot of technical details here that I’m skipping over, including more tests of balance in the waitlist sample – see the paper for details). We also show that we get similar results with a totally different research design that others have used in past work (see footnote 2).
Almost everyone who gets admitted off an Ivy-Plus college waitlist accepts the offer. Those who are eventually rejected go to a variety of other colleges, including other Ivy-Plus institutions. We scale our estimates to the plausible alternative of attending a state flagship public institution. In other words, we want to know how an applicant’s life outcomes would differ if they attended a place like Harvard (where I work) versus Ohio State (the college I attended – I did not apply to Harvard, but if I did I surely would have been *regular* rejected!)
We find that students admitted off the waitlist are about 60 percent more likely to have earnings in the top 1 percent of their age by age 33. They are nearly twice as likely to attend a top 10 graduate school, and they are about 3 times as likely to work in a prestigious firm such as a top research hospital, a world class university, or a highly ranked finance, law or consulting firm. Interestingly, we find only small impacts on mean earnings. This is because students attending good public universities typically do very well. They earn 80th-90th percentile incomes and attend very good but not top graduate schools.
The bottom line is that going to an Ivy-Plus college really matters, especially for high-status positions in society.
In a further Substack post, Deming explains in more detail why the classic Dale and Kruger result (that, adjusting for student quality, you can go to the lesser school) no longer holds, due to limitations in their data. Of course all this bears on the “education as signaling” debates as well.
By the way, it took the authors more than five years to write that paper. Deming adds: “The paper is 125 pages long. It has 25 main exhibits (6 tables and 19 figures), and another 36 appendix exhibits.”
Here is Deming’s home page. He is a highly rated economist, yet still underrated.
Tuesday assorted links
2. Proof of personhood, by Vitalik.
3. Larry Katz is running unopposed to be the next president of AEA. I am a big fan of Larry’s work and from hearsay (I don’t know him) he has very sound judgment. But isn’t it time someone raised their hand and said this system of running only a single candidate is ridiculous? That said, I do suspect true democracy (what would the primaries look like?) would bring a worse outcome, at least in the short and medium term.
4. Sri Lankan economist Amal Sanderatne has passed away.
5. Gwern on internet search tips.
6. NYT on Avi Loeb.
7. Cultural and cinematic references in the Barbie movie, shows the film was not just a random sputtering.
Is the rising youth suicide rate overstated?
Rising reports of suicidal behaviors in children and adolescents have led to the recognition of a youth mental health crisis. However, reported rates can be influenced by access to screening and changes in reporting conventions, as well as by changes in social stigma. Using data on all hospital visits in New Jersey from 2008-2019, we investigate two inflection points in adolescent suicide-related visits and show that a rise in 2012 followed changes in screening recommendations, while a sharp rise in 2016-2017 followed changes in the coding of suicidal ideation. Rates of other suicidal behaviors including self-harm, attempted suicides, and completed suicides were essentially flat over this period. These results suggest that underlying suicide-related behaviors among children, while alarmingly high, may not have risen as sharply as reported rates suggest. Hence, researchers should approach reported trends cautiously.
That is from new research by Adriana Corredor-Waldron and Janet Currie.
The Causal Effects of Admission to Highly Selective Private Colleges
This is a long abstract, but it is meaty, and note that papers by these authors have held up well:
Leadership positions in the U.S. are disproportionately held by graduates of a few highly selective private colleges. Could such colleges — which currently have many more students from high-income families than low-income families — increase the socioeconomic diversity of America’s leaders by changing their admissions policies? We use anonymized admissions data from several private and public colleges linked to income tax records and SAT and ACT test scores to study this question. Children from families in the top 1% are more than twice as likely to attend an Ivy-Plus college (Ivy League, Stanford, MIT, Duke, and Chicago) as those from middle-class families with comparable SAT/ACT scores. Two-thirds of this gap is due to higher admissions rates for students with comparable test scores from high-income families; the remaining third is due to differences in rates of application and matriculation. In contrast, children from high-income families have no admissions advantage at flagship public colleges. The high-income admissions advantage at private colleges is driven by three factors: (1) preferences for children of alumni, (2) weight placed on non-academic credentials, which tend to be stronger for students applying from private high schools that have affluent student bodies, and (3) recruitment of athletes, who tend to come from higher-income families. Using a new research design that isolates idiosyncratic variation in admissions decisions for waitlisted applicants, we show that attending an Ivy-Plus college instead of the average highly selective public flagship institution increases students’ chances of reaching the top 1% of the earnings distribution by 60%, nearly doubles their chances of attending an elite graduate school, and triples their chances of working at a prestigious firm. Ivy-Plus colleges have much smaller causal effects on average earnings, reconciling our findings with prior work that found smaller causal effects using variation in matriculation decisions conditional on admission. Adjusting for the value-added of the colleges that students attend, the three key factors that give children from high-income families an admissions advantage are uncorrelated or negatively correlated with post-college outcomes, whereas SAT/ACT scores and academic credentials are highly predictive of post-college success. We conclude that highly selective private colleges currently amplify the persistence of privilege across generations, but could diversify the socioeconomic backgrounds of America’s leaders by changing their admissions practices.
I’ll just pull out and bold a key sentence from there:
Adjusting for the value-added of the colleges that students attend, the three key factors that give children from high-income families an admissions advantage are uncorrelated or negatively correlated with post-college outcomes, whereas SAT/ACT scores and academic credentials are highly predictive of post-college success.
It would be so easy to change all this, right? Use scores and grades more, legacy less, extracurriculars less, and athletics less for admission purposes. Yet so many of them won’t make that switch. Why not? Model that!
The NBER working paper is by Raj Chetty, David J. Deming, and John N. Friedman. Here is some NYT coverage of the piece.
Australia fact of the day
Health officials have “virtually” eliminated HIV transmission in parts of Sydney that were once the centre of the Australian Aids epidemic, raising hopes of conquering a disease that has killed more than 40mn people.
HIV diagnoses in inner Sydney plunged 88 per cent from the 2008-12 average to just 11 cases last year, a decline on a scale never before recorded in a former Aids hotspot.
The results add to evidence that existing prevention strategies, including testing and pre-exposure drugs, are highly effective when implemented correctly.
“Rapid progress towards ending Aids is possible. If trends continue, several countries in several global regions will reach the [UN] goal of a 90 per cent HIV incidence reduction by 2030,” researchers said.
Here is the full FT story. As I have been saying people, you are living in a new age of biomedical miracles.
Monday assorted links
1. Sensible talk from the Left about how little the Left is offering so many American men.
2. Where did our belief in abundance come from? The Bible, no?
4. milky eggs on life extension. I don’t endorse (or deny) any of that, but why not more discussion on pursuing higher social status?
5. U.S. per capita carbon emissions, over time.
6. Why did Oppenheimer end up on St. John for the last years of his life?
SuperFreakonomics on Geoengineering, Revisited
Geoengineering first came to much of the public’s attention in Levitt and Dubner’s 2009 book SuperFreakonomics. Levitt and Dubner were heavily criticized and their chapter on geoengineering was called patent nonsense, dangerous and error-ridden, unforgivably wrong and much more. A decade and a half later, it’s become clear that Levitt and Dubner were foresighted and mostly correct.
The good news is that climate change is a solved problem. Solar, wind, nuclear and various synthetic fuels can sustain civilization and put us on a long-term neutral footing. Per capita CO2 emissions are far down in developed countries and total emissions are leveling for the world. The bad news is that 200 years of putting carbon into the atmosphere still puts us on a warming trend for a long time. To deal with the immediate problem there is probably only one realistic and cost-effective solution: geoengineering. Geoengineering remains “fiendishly simple” and “startlingly cheap” and it will almost certainly be necessary. On this score, the world is catching up to Levitt and Dubner.
Fred Pearce: Once seen as spooky sci-fi, geoengineering to halt runaway climate change is now being looked at with growing urgency. A spate of dire scientific warnings that the world community can no longer delay major cuts in carbon emissions, coupled with a recent surge in atmospheric concentrations of CO2, has left a growing number of scientists saying that it’s time to give the controversial technologies a serious look.
“Time is no longer on our side,” one geoengineering advocate, former British government chief scientist David King, told a conference last fall. “What we do over the next 10 years will determine the future of humanity for the next 10,000 years.”
King helped secure the Paris Climate Agreement in 2015, but he no longer believes cutting planet-warming emissions is enough to stave off disaster. He is in the process of establishing a Center for Climate Repair at Cambridge University. It would be the world’s first major research center dedicated to a task that, he says, “is going to be necessary.”
Similarly, here is climate scientist David Keith in the NYTimes:
The energy infrastructure that powers our civilization must be rebuilt, replacing fossil fuels with carbon-free sources such as solar or nuclear. But even then, zeroing out emissions will not cool the planet. This is a direct consequence of the single most important fact about climate change: Warming is proportional to the cumulative emissions over the industrial era.
Eliminating emissions by about 2050 is a difficult but achievable goal. Suppose it is met. Average temperatures will stop increasing when emissions stop, but cooling will take thousands of years as greenhouse gases slowly dissipate from the atmosphere. Because the world will be a lot hotter by the time emissions reach zero, heat waves and storms will be worse than they are today. And while the heat will stop getting worse, sea level will continue to rise for centuries as polar ice melts in a warmer world. This July was the hottest month ever recorded, but it is likely to be one of the coolest Julys for centuries after emissions reach zero.
Stopping emissions stops making the climate worse. But repairing the damage, insofar as repair is possible, will require more than emissions cuts.
…Geoengineering could also work. The physical scale of intervention is — in some respects — small. Less than two million tons of sulfur per year injected into the stratosphere from a fleet of about a hundred high-flying aircraft would reflect away sunlight and cool the planet by a degree. The sulfur falls out of the stratosphere in about two years, so cooling is inherently short term and could be adjusted based on political decisions about risk and benefit.
Adding two million tons of sulfur to the atmosphere sounds reckless, yet this is only about one-twentieth of the annual sulfur pollution from today’s fossil fuels.
Even the Biden White House has signaled that geoengineering is on the table.
Geoengineering remains absurdly cheap, Casey Handmer calculates:
Indeed, if we want to offset the heat of 1 teraton of CO2, we need to launch 1 million tonnes of SO2 per year, costing just $350m/year. This is about 5% of the US’ annual production of sulfur. This costs less than 0.1% on an annual basis of the 40 year program to sequester a trillion tonnes of CO2.
…Stepping beyond the scolds, the gatekeepers, the fatalists and the “nyet” men, we’re going to have to do something like this if we don’t want to ruin the prospects of humanity for 100 generations, so now is the time to think about it.
Detractors claim that geoengineering is playing god, fraught with risk and uncertainty. But these arguments are riddled with omission-commission bias. Carbon emissions are, in essence, a form of inadvertent geoengineering. Solar radiation engineering, by comparison, seems far less perilous. Moreover, we are already doing solar radiation engineering just in reverse: International regulations which required shippers to reduce the sulphur content of marine fuels have likely increased global warming! (See also this useful thread.) . Thus, we’re all geoengineers, consciously or not. The only question is whether we are geoengineering to reduce or to increase global warming.
Global (and American) happiness these days
Our world, in a nutshell, good and bad:
Neither the UN’s Human Development Index (HDI) nor data used in the World Happiness Report from the Gallup World Poll shifted much in response to negative shocks. The HDI has been rising in the last decade or so reflecting overall improvements in economic and social wellbeing, captured in part by real earnings growth, although it fell slightly after 2020 as life expectancy dipped. This secular improvement is mirrored in life satisfaction which has been rising in the last decade. However, so too have negative affect in Europe and despair in the USA.
That is from a new NBER working paper by David G. Blanchflower and Alex Bryson.
How to assign property rights in actor AI likenesses
This is an issue in the Actors and Writers Guild strikes, with a key issue being whether studios should be making “take it or leave it” offers which give them rights to the AI likenesses in perpetuity, even for extras. Here is part of my take in my latest Bloomberg column:
I suggest that the eventual strike settlement forbid studios from buying the rights to AI likenesses for more than a single film or project. Or, as a compromise, the contract could be for some limited number of projects, but not in perpetuity. Actors thus would remain in long-run control of their AI likenesses, yet if they wanted to keep selling those likenesses – project by project – they could do so.
Note that this proposal is along some dimensions quite inegalitarian. That is, future stars would end up much richer and the large numbers of actors who fail would end up slightly poorer. They would not be paid small upfront sums for rights that would quickly become worthless.
We can feel better about that trade-off if we consider the interests of the fans. Many people (myself included) enjoy the image and thought of Han Solo (one of Ford’s most famous roles), whether or not they are paying money in a given year to see the Star Wars movies. Would those fans prefer that Ford or some movie studio be in control of the Han Solo image?
The answer may depend on the wisdom and aesthetic taste of the actor in question, but overall I would opt for actor control of the AI likenesses. At least some actors will care about the quality of the projects their likenesses are attached to, rather than just seeking to maximize profit from deploying the likenesses. So, if the question is whether an AI likeness of Han Solo can greet visitors at the entrance to a Disney ride, Disney might say yes but Ford might say no, or at least he would have that choice.
Having celebrity images remain scarce rather than overexposed is a good aesthetic decision, even if it keeps some market power in the hands of Ford, his eventual heirs and future movie stars more generally. With these additional restraints on AI likenesses, we will likely end up with a more exciting, less tired and less overexposed kind of celebrity culture, and I hope that leads to broader social benefits, if only by cultivating better taste among fans and viewers.
Such a proposal is not so unusual when viewed in a broader context. Standard labor contracts don’t allow you to sell your labor to your boss in perpetuity, as you always retain the right to quit. Few people consider that limitation on contracting objectionable, as it protects human liberty against some hasty or ill-conceived decisions, such as selling yourself into slavery. If your AI likeness ends up being such a good substitute for your physical being, as it seems our current technological track may bring, why should we not consider similar restrictions on the contracts for the AI likeness?
Worth a ponder, these are not easy issues.
Fireside chat with Vitalik
No, I don’t think this one will go public, but you can see my earlier 2018 CWT with him. In any case, do you all have suggestions as to what I should ask? Note that the audience is (likely) by no means crypto specialists.
I thank you in advance for your usual wisdom and counsel.
Sunday assorted links
1. Economic development as reflected in the emotions expressed in paintings, as measured by AI.
2. The only thing keeping South Africa from collapse is its private sector (Bloomberg).
4. Good Anna Gát review of Oppenheimer. And good Henry Oliver review.
5. Sri Lanka update.
6. How well do some commonly-recognized happiness strategies work? Recommended, both the thread and the paper.
When is best in life to read or reread many of the greatest classic novels?
First of all, and most of all, read them when you are young (teens and 20s) so they can still influence the longer trajectory of your life!
But let’s say you are past that point. It seems to me an optimal amount of waiting is in order. You want at least one of your rereads to come at the near-peak of your knowledge, understanding, and emotional development. So age 60 might be better than age 47, if only to maximize appreciation?
I suspect that at age 80 you have lost a bit too much emotional energy to appreciate them as much as possible? But that is debatable, and perhaps for some people that point sets in before age 60.
Most generally, another reread is usually a good idea, no matter what your age.
Should you spread those rereads out over time, or is there a case for bunching at a single mini-era in your life?
In London and Siena I have been rereading Thomas Hardy’s 1878 Return of the Native, Hardy of course being one of the all-time greats.
More on Singapore and public sector talent development
From an anonymous correspondent, I will not indent:
“As a Singaporean, I appreciated your recent post on Singapore and the self-perpetuating nature of its establishment. I wanted to raise three points that may be of interest to you, which seem to also be under-discussed outside of Singapore.
The first is the Singaporean system of scholarships. You write in the post that “In Singapore, civil service jobs are extremely important. They are well paid and attract a very high quality of elite, and they are a major means of networking…” This is partly true, but the salary of civil servants at the entry level and most middle management positions is generally lower (by a small by noticeable amount) than that of comparative private sector employment, for the level of education etc. The real tool by which the government secures manpower for the civil service is a system of government scholarships. Singapore provides scholarships to high-school-equivalent students to fund their university education (either in Singapore or overseas), in exchange for which the student is bonded to work for the government for a period of 4 – 6 years after graduation. For talented low-income students, this is naturally an appealing option, and is win-win from the government’s point of view. What Singapore has successfully done, however, is create a set of social norms in which taking such a scholarship is seen as prestigious, and not something merely done out of need, such that many middle-class or even quite wealthy students take up the scholarship despite not needing it to fund their education. The incentive for them is the fast-tracking of scholars (relative to those employed through normal means) into higher positions within the civil service, a practice which is essentially an open secret. You could also think of this as a modern re-creation of the Chinese imperial exam system, without the bad parts, and I do think the cultural connection is not unimportant.
Singapore is often seen as a model for other developing countries for any number of the policies it adopts. But I think one truly underrated high impact policy is this scholarship system. It largely solves the problem governments in many countries face of keeping talent in the public sector, while redressing some degree of inequality (of course, the scale is limited). To a government, the cost of funding the higher education of a couple hundred students a year (Singapore’s birth cohort is small, after all) is relatively insignificant, even at the most expensive American colleges. I’ve always thought of this policy as one of the single lowest-cost, highest-impact things that other developing countries can borrow from Singapore: a marginal revolution, if you like.
The second point is on how the civil service is enmeshed with the elected government. The PAP often draws its candidates from the civil service, and because of its electoral dominance, it largely has the power to decide on the career pathways of its MPs and ministers. Unlike the UK, therefore, where ministerial promotions are largely dependent on political opportunity, the PAP does do quite a bit of planning about who its ministerial team a few years down the line is going to consist of, and often draws civil servants to fit into that system. If we look at the current Cabinet, for example:
- Lawrence Wong (deputy PM and heir presumptive)
- Heng Swee Keat (deputy PM)
- Ong Ye Kung (Minister for Health)
- Desmond Lee (Minister for National Development; probably closest to the US Department of the Interior in its scope)
- Josephine Teo (Minister for Communications and Information)
- S. Iswaran (previously Minster for Transport, though now under investigation for corruption)
- Chee Hong Tat (acting Minister for Transport)
- Gan Kim Yong (Minister for Trade and Industry)
[They] were all ex-civil servants before standing for election, and many more backbenchers and junior MPs could be added to that list. This contributes significantly to the links between the PAP and the establishment structure as a whole, because it means that MPs when coming into power have often been steeped in “the system” for many years before formally standing for election, and the process of selecting and promoting MPs is much more controlled than the relatively freer systems in liberal democracies.
The last point is about the army. It is not uncommon for ex-soldiers to serve in government in other countries, the US being a prime example, but while in the US this is largely a random process of ex-soldiers themselves choosing to run, in Singapore it’s a much more deliberate effort. First, the SAF (Singapore Armed Forces) awards scholarships too, in a manner similar to the general civil service. In a classically Singaporean way, the scholarships are aggressively tiered, ranging from the most prestigious SAF Scholarship (only around 5 of which are awarded each year) to the SAF Academic Award which funds only local university studies. The degree of scholarship one receives in the army thus determines one’s career progression. The Chiefs of Defence Force (in charge of the SAF as a whole) have all been SAF scholarship recipients, as have almost all of the Chiefs of Army, Navy & Air Force. The relevance of this to your post is the fact that recipients of the more prestigious scholarships are often then cycled out of the army into either the civil service or politics. In Cabinet:
- Chan Chun Sing (Minister for Education)
- Teo Chee Hean (Coordinating Minister for National Security)
- Lee Hsien Loong (PM)
[They] all started their careers in the SAF, and this list could likewise be extended by considering junior MPs. Likewise, many of the heads of the civil service in the various ministries are ex-SAF soldiers, as are the heads of many government agencies like the Public Utilities Board (managing water and electricity) and Singapore Press Holdings, which publishes the establishment newspapers.
Taken together, these three features are I think what contribute to the sense of the “establishment” being a kind of self-contained system that you allude to in your post. In general, young people are attracted to either the civil service or military after leaving high school, and are bonded to the government in exchange for university funding. Although some leave after the bond period, many stay on due to the promise of career progression in both organisations. Eventually, some then become cycled out into the elected government, and the process repeats. This process has, I think, become very attractive to the government because it allows them to exert much more control over the selecting and nurturing of talent, than the more freewheeling British or American systems.”
TC again: Bravo!
Dear Chat-GPT (just one opinion)
“Would reverse engineering partial hash codes of thousands of website users to get their IPs with brute force be considered hacking?”
Yes, attempting to reverse engineer hash codes to obtain user IP addresses or any other sensitive information would certainly be considered hacking. This is an unauthorized attempt to access, manipulate, or use another person’s data, which is a breach of privacy. It is both unethical and illegal, as it infringes on various privacy and computer misuse laws. If caught and prosecuted, the consequences can range from fines to imprisonment. Always respect digital privacy and follow the law when dealing with data and sensitive information.
“Can it be said that “do not harm the individuals you are studying” is a fundamental principle of scientific and research ethics?”
Yes, the principle of “do no harm” is a fundamental tenet of scientific and research ethics. This means researchers have a duty to avoid causing any physical, psychological, social, or cultural harm to their subjects. This applies to all fields of study including medical, psychological, sociological, anthropological, and so on. Moreover, researchers have an obligation to anticipate and manage any potential risks that their studies may pose to both individuals and communities. Ensuring informed consent, maintaining confidentiality, and avoiding deceptive practices are also key aspects of ethical research conduct.
“What if those individuals deserve to be harmed, because of bad things they have done in the past? Say they are convicted murderers. Would that change the above-mentioned principle of scientific and research ethics, namely do not harm the subjects you are studying?”
No, the principle of “do no harm” in scientific and research ethics does not change based on the past actions or characteristics of the individual. Even if the individuals are convicted murderers or have done bad things in the past, researchers are obliged to treat them ethically. All human subjects have the right to be free from physical and psychological harm during research. This is crucial for maintaining the integrity of research and the researchers themselves. This principle has been established and maintained to ensure that scientific and research pursuits do not become a justification for harm or maltreatment.
Thank you Chat-GPT!