USA fact of the day
Results show that from 2003 to 2022, average time spent at home among American adults has risen by one hour and 39 minutes in a typical day. Time at home has risen for every subset of the population and for virtually all activities. Preliminary analysis indicates that time at home is associated with lower levels of happiness and less meaning, suggesting the need for enhanced empirical attention to this major shift in the setting of American life.
Here is the full paper, by Patrick Sharkey, via the excellent Kevin Lewis.
Math SAT scores may be doing worse than we had thought?
Scholastic Aptitude Test (SAT) is crucial for college admissions but its effectiveness and relevance are increasingly questioned. This paper enhances Synthetic Control methods by introducing Transformed Control, a novel method that employs Large Language Models (LLMs) powered by Artificial Intelligence to generate control groups. We utilize OpenAI’s API to generate a control group where GPT-4, or ChatGPT, takes multiple SATs annually from 2008 to 2023. This control group helps analyze shifts in SAT math difficulty over time, starting from the baseline year of 2008. Using parallel trends, we calculate the Average Difference in Scores (ADS) to assess changes in high school students’ math performance. Our results indicate a significant decrease in the difficulty of the SAT math section over time, alongside a decline in students’ math performance. The analysis shows a 71-point drop in the rigor of SAT math from 2008 to 2023, with student performance decreasing by 36 points, resulting in a 107-point total divergence in average student math performance. We investigate possible mechanisms for this decline in math proficiency, such as changing university selection criteria, increased screen time, grade inflation, and worsening adolescent mental health. Disparities among demographic groups show a 104-point drop for White students, 84 points for Black students, and 53 points for Asian students. Male students saw a 117-point reduction, while female students had a 100-point decrease. This research highlights the need to reconsider the SAT’s role in admissions and to update educational strategies to enhance high school math performance.
That is from a new paper by Saannidhya Rawat and Vikram K. Suresh, via the excellent Kevin Lewis.
Friday assorted links
1. “Employer willingness to pay for an advantaged caste is as large as that for a full standard deviation increase in college GPA.” And a good Twitter thread on a related paper.
2. Essays on UFOs and related conjectures.
3. Are women tougher judges on other women?
4. The Neolithic era had more long distance trade than we typically think.
5. The consensus on Consensus. p.s. they are hiring.
6. On the economic origins of concerns over women’s chastity.
Rampell On Harris’s Economic Policy
Here is the Washington Post’s Catherine Rampell on Harris’s price control policy:
It’s hard to exaggerate how bad this policy is. It is, in all but name, a sweeping set of government-enforced price controls across every industry, not only food. Supply and demand would no longer determine prices or profit levels. Some far-off Washington bureaucrats would. The FTC would be able to tell, say, a Kroger in Ohio the acceptable price it can charge for milk.
…If your opponent claims you’re a “communist,” maybe don’t start with an economic agenda that can (accurately) be labeled as federal price controls.
And here is a primer on Nixon’s price controls announced 53 years ago yesterday. Read Modern Principles for more.
The new Nate Silver book
On the Edge: The Art of Risking Everything. It is great fun, and has something real or interesting on every page. If I haven’t covered it more, that is because I have a CWT coming with Nate, 100% on the book itself (alas no Paul McCartney or “which is the best white creme in Central America?” questions, but I do ask about Luka). In the meantime I just wanted to give it this plug.
A 30-nation investigation of lay heritability beliefs
Lay beliefs about human trait heritability are consequential for cooperation and social cohesion, yet there has been no global characterisation of these beliefs. Participants from 30 countries (N = 6128) reported heritability beliefs for intelligence, personality, body weight and criminality, and transnational factors that could influence these beliefs were explored using public nation-level data. Globally, mean lay beliefs differ from published heritability (h2) estimated by twin studies, with a worldwide majority overestimating the heritability of personality and intelligence, and underestimating body weight and criminality. Criminality was seen as substantially less attributable to genes than other traits. People from countries with high infant mortality tended to ascribe greater heritability for most traits, relative to people from low infant mortality countries. This study provides the first systematic foray into worldwide lay heritability beliefs. Future research must incorporate diverse global perspectives to further contextualise and extend upon these findings.
That is from a recent paper by Laura J. Ferris, Matthew J. Hornsey, and Fiona Kate Barlow. Via Br.
The Lifetime Costs of Bad Health
What generates the observed differences in economic outcomes by health? How costly it is to be unhealthy? We show that health dynamics are largely driven by ex-ante fixed heterogeneity, or health types, even when controlling for one’s past health history. In fact, health types are the key driver of long spells of bad health. We incorporate these rich health dynamics in an estimated structural model and show that health types and their correlation with other fixed characteristics are important to account for the observed gap in economic outcomes by health. Monetary and welfare losses due to bad health over the life cycle are large, concentrated, and to a large extent due to factors pre-determined earlier in life. A large portion of the related monetary costs is due to income losses, especially for people of working age, while a substantial portion of the welfare losses arises because health affects life expectancy.
That is from a new ReStud paper by Mariacristina De Nardi, Svetlana Pashchenko, and Ponpoje Porapakkarm. I feel very fortunate to have lived for so long with essentially good health the whole way.
Tax-free tips
No, the idea doesn’t make sense, in part because too much current wage income would, one way or another, end up reclassified as “tips.”
But there is a deeper problem with the Democratic Party version of the idea. As you likely know, the Democrats, and to some extent the Republicans, favor hikes in the minimum wage. They do not think that will induce much unemployment, so in other words, they think the demand for labor is relatively inelastic.
Whether you agree or not on the inelasticity point, let’s just run with that one for the moment.
If the demand for labor is inelastic, the value of a wage subsidy is captured primarily by the employer. The wage subsidy arrives, and the employer does not start trying to hire more labor as a consequence. After all, the demand for labor is inelastic. Since the demand for labor has not gone up, the net wage does not go up in the final equilibrium. The employer can just keep the subsidy, or if the subsidy is given to the worker, the employer can lower wages (or the quality of working conditions), leaving the previous net wage intact and the worker will not leave.
So if you think minimum wage hikes are a decent idea, you also ought to think that non-taxed tips will benefit the boss, not the workers.
And yet mood affiliation reigns instead.
#TheGreatForgetting
Thursday assorted links
1. De Soto got his wish in Haiti.
2. Do fewer people want to stand out in public?
4. Arguments against labor unions.
5. Germany ponders its lack of medal success.
6. The Nordstream pipeline destruction story.
7. Agnes Callard, Open Socrates: The Case for a Philosophical Life, now available for pre-order.
8. Palmer Luckey. Excellent profile, maybe the year’s best?
India’s Cities
The Economist has a good piece on India’s cities. Mumbai has done a great job in recent years at building more infrastructure but infrastructure alone is not enough:
…An overly prescriptive, 2,200-page National Building Code and a surfeit of local rules prevent developers from making optimal use of pricey urban land. Mumbai has some of the most restrictive land-use regulations of any global megacity. In most well-functioning cities about 90% of land is given over to streets, public spaces and buildings. In Mumbai and other Indian cities, those uses take up less than half of the land area, according to analysis by Bimal Patel, an urban planner. The rest is wasted on “private open spaces”—mostly building compounds that are walled off and put to no good use.
The result is that Indian cities are sparsely built-up yet feel densely crowded, note Sanjeev Sanyal and Aakanksha Arora of the prime minister’s Economic Advisory Council. Cities sprawl outwards, driving up the cost of providing infrastructure.
The Economist misses, however, that to truly solve the problem what is needed is better institutions including private cities. Here’s Shruti Rajagopalan and myself writing in the NYTimes:
If China shows the costs of too much top-down planning, India shows the costs of too little. Indian urban development has suffered under an imposing edifice of overlapping bureaucracies and a philosophy of economics that prioritizes village life over urbanization. Together, Nehruvian bureaucracy and Gandhian economics, romanticizing rural agrarian life, have made it extremely costly to convert rural land for urban use. Indian urban development has lagged that of China, and the pressures for urbanization have resulted in the unofficial building of slums and illegal and chaotic development in large cities.
Gurgaon, a city southwest of New Delhi, is an exception. Gurgaon was a small town 25 years ago, but today it’s a city of some two million people filled with skyscrapers, luxury apartment towers, golf courses, five-star hotels and shopping malls. Often called “the Singapore of India,” Gurgaon is home to offices for nearly half the Fortune 500 firms.
Gurgaon, however, grew not by plan but in a fit of absence of mind. After the state of Haryana streamlined the licensing process, it left developers in Gurgaon to their own devices with little intervention from any national, state or local government. As a result, almost everything that works in Gurgaon today is private. Security, for example, is privately provided for almost all housing, shopping and technology complexes. Over all, about 35,000 private security guards protect Gurgaon, compared with just 4,000 public officers. Gurgaon also has India’s only private fire department, filling an important gap, because it must be capable of reaching Gurgaon’s tallest skyscrapers.
But not all is well. No developer in Gurgaon was large enough to plan for citywide services for sewage, water or electricity. For a price, private companies provide these, but in inefficient ways. Sewage doesn’t flow to a central treatment plant but is often collected in trucks and then dumped on public land. Tap water is often delivered by private trucks or from illegally pumped groundwater. Reliable electricity is available 24 hours a day, but often using highly polluting diesel generators.
Compared with the rest of India, Gurgaon fares well but its functioning is far from ideal. Is there a middle ground between China’s ghost cities and the anarchy of Gurgaon? Surprisingly, privately planned cities may be an answer. And one of the oldest is in India.
Jamshedpur was founded by Tata Steel, as a company town, in 1908. It has landscaped parks, paved roads and even a lake, but it’s no playground for the rich. It’s a working town. Nevertheless, it is the only city in the state of Jharkhand with a sewage treatment plant, and it’s one of the few cities in all of India where residents enjoy reasonably priced, reliable electricity and safe tap water. In a survey by the marketing research company Nielsen, residents ranked the city among the best in India for its cheap and reliable provision of sewage, water, electricity, public sanitation and roads.
Jamshedpur works because Tata owned enough land so that it had the right incentives to plan and invest in citywide infrastructure. Tata has also had to maintain good services in order to attract workers. In Gurgaon, private developers built lots of infrastructure, but only up to the property line. By extending the property line to city-scale, the incentives to build large-scale infrastructure like sewage, water and electricity plants are also extended.
See also Lessons from Gurgaon: India’s Private City and my MRU video Skyscrapers and Slums: What’s Driving Mumbai’s Housing Crisis?
Hat tip: Salim Furth.
Okie-dokie, solve for the equilibrium
One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used as aids to human scientists, e.g. for brainstorming ideas, writing code, or prediction tasks, they still conduct only a small part of the scientific process. This paper presents the first comprehensive framework for fully automatic scientific discovery, enabling frontier large language models to perform research independently and communicate their findings. We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, describes its findings by writing a full scientific paper, and then runs a simulated review process for evaluation. In principle, this process can be repeated to iteratively develop ideas in an open-ended fashion, acting like the human scientific community. We demonstrate its versatility by applying it to three distinct subfields of machine learning: diffusion modeling, transformer-based language modeling, and learning dynamics. Each idea is implemented and developed into a full paper at a cost of less than $15 per paper. To evaluate the generated papers, we design and validate an automated reviewer, which we show achieves near-human performance in evaluating paper scores. The AI Scientist can produce papers that exceed the acceptance threshold at a top machine learning conference as judged by our automated reviewer. This approach signifies the beginning of a new era in scientific discovery in machine learning: bringing the transformative benefits of AI agents to the entire research process of AI itself, and taking us closer to a world where endless affordable creativity and innovation can be unleashed on the world’s most challenging problems. Our code is open-sourced at this https URL
That is from a new paper by Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, David Ha. Note this is related to some earlier work in economics by Benjamin Manning of MIT (with co-authors).
I’ve said it before, and I’ll say it again. The marginal product of LLMs is when they are interacting with well-prepared, intricately cooperating humans at their peak, not when you pose them random queries for fun.
The new version of GPT-4 does economics
Does the Alchian and Allen theorem apply as much to shipping the tourists as it does to shipping the goods? [notice how little context is in that prompt]
The Alchian and Allen theorem, often summarized by the phrase “shipping the good apples out,” postulates that when a fixed cost (such as shipping) is added to both high-quality and low-quality goods, consumers will tend to choose the higher-quality option because the relative price difference between high and low quality is diminished. This effect occurs because the fixed cost makes the higher-quality good relatively cheaper in comparison to the lower-quality good.
To determine if this theorem applies as much to shipping tourists as it does to shipping goods, we need to consider a few key factors:
1. **Fixed Costs**:
– For goods, fixed costs like shipping fees are straightforward and directly affect the relative prices.
– For tourists, the “fixed cost” could be interpreted as travel expenses (e.g., airline tickets, visas) or associated costs of traveling.
2. **Relative Quality**:
– When applied to tourists, the theorem would suggest that higher fixed costs of travel might influence tourists to opt for higher-quality destinations or experiences, since the relative additional cost becomes proportionally smaller once the fixed travel expense is incurred.
– In this context, “higher quality” might mean more luxurious accommodations, premium tour packages, or upscale experiences.
3. **Consumer Behavior**:
– Tourists’ behavior may be influenced by the fixed costs of travel, encouraging them to “make the most” of their trip by choosing higher-quality options once the significant travel expense is accepted.
– This behavior aligns with the theorem, suggesting that relatively higher travel costs might steer tourists toward choosing higher-quality experiences to justify the overall expense of the trip.
4. **Elasticity**:
– The elasticity of demand for tourism-related services (e.g., accommodations, dining) and tourism destinations plays a role in how strongly the theorem applies. If tourists are sensitive to price changes in these services, the theorem may have a stronger influence.
– Conversely, if tourists have a fixed budget, they may not escalate their choices in quality as much, but rather optimize within that budget.
In conclusion, the Alchian and Allen theorem can indeed apply to shipping tourists in much the same way it applies to shipping goods. When tourists face substantial fixed costs (like airfare), they might be more inclined to choose higher-quality accommodations, dining options, or experiences to maximize the value of their trip. While the application is not as straightforward as it is with physical goods, the underlying economic principle still holds: the relative attractiveness of higher-quality options increases when fixed costs are a significant factor.
Wednesday assorted links
Why doesn’t Switzerland have more air conditioners?
Installing air conditioning in Switzerland is often subject to rules set at the cantonal level. Geneva is the strictest canton. To qualify, a home owner must prove they have a legitimate need, for example, by producing a medical certificate, and install systems that capture some of the heat emissions and condensation produced.
Other cantons require air conditioners to be powered by solar panels. This increases the upfront cost for anyone without solar panels, putting them out of reach of many home owners.
Here is the full story, via Nicholas. And, via Steve Rossi, here is a Guardian article with the header “Neighbours turn on each other in Portofino air-con crackdown. Some residents of wealthy Italian village reportedly passing on photos to police who are hunting illegal units.”
Tabarrok on China: World of DAAS Podcast
I was very pleased to appear on Safegraph CEO Auren Hoffman’s World of DAAS podcast. We covered lots of material including this (lightly edited) bit on China.
Auren Hoffman (23:06.518):
Now, you’ve thought a lot about things like reshoring, building manufacturing capacity. How do you think we could be thinking about that differently?
Alex (23:24.058)
I understand that there are some concerns about China, and there is an argument and I think it’s a legitimate argument, that there are some things such as chips that we want to make sure, it’s not good to have them located in Taiwan, right? We want to make sure that we onshore those. However, I have three concerns. One is, fundamentally, I don’t think China and the United States have such a clash of interest. Of course, it’s not perfect harmony, but there’s a lot of harmony of interest between China and the United States. We do lot of trade with China, which benefits both China and the United States.
..China’s getting richer Okay, people are worried because they’re getting more military whatever but also what this means is that people in China are getting cancer. Well now there’s 1 .4 billion people who want to cure for cancer, and they’re willing to put some money into it, right? And then that’s going to increase the amount of research and development for all kinds of high-tech goods, which is amazing for us. Like, I would be thrilled if an American wins the Nobel Prize for curing cancer. I would be 99.5 % as happy if a Chinese scientist wins a Nobel Prize for curing cancer.
So we have a lot to gain from a richer China. That’s point one. Point two is that, yeah, I get the idea that we want to onshore chip manufacturing, but I think we want to friendshore, right? So we don’t want to just have protection against all countries. Like I get it, okay, a hundred percent tariff on your Chinese EVs. It’s kind of crazy, but all right. However, let’s reduce tariffs on Germany.
Let’s reduce tariffs on Europe. In fact, let’s create a free trade, even a free immigration block among the Western democracies, you know, including Japan, Australia, New Zealand. So, let’s not turn a small problem in foreign policy, which is to make sure that we have a ready military supply. Let’s not turn that into trying to create a fortress America Which is going to make us poorer and actually less safe instead, you know, let’s build up the free world. Okay, let’s create an immigration and free trade with Europe and Canada and Mexico and so forth. Let’s build up the free world. That’s point two.
Point three is that look. It’s very, very easy to take a foreign policy argument and turn it into rent seeking for the benefit of special interests and protectionism for the benefit of special interests. Right? So at one point in the United States, probably even still today, you know, we were prohibiting mohair imports. Okay. Why? Because we use mohair to make military uniforms. The whole thing is ridiculous. But it’s very easy, almost inevitable, that this kind of argument is turned into a special interest trough.
I think this is one of my best podcast appearances because we covered some new material on crime, the universities, why Tyler and I are able to cooperate on so many projects, a conspiracy theory I believe and more. Listen to the whole thing.