Thursday, March 30, 2023
The Economist calls it "a hellish-perfect-dumpster-fire-storm."
The situation poses a problem for two big, intertwined American industries. The first is property, where owners are grappling with the idea that the office buildings they own—uncomfortably empty and unlikely to fill up again—might only be worth half what they paid for them. The second is their financiers. When Brookfield, an asset manager, recently decided it would be better off handing over the keys of two vast office towers in Los Angeles, rather than refinancing the $784m of loans it owed on them, it handed the keys over to Citigroup and Morgan Stanley, two big banks.
Banks will end up responsible for lots of offices, which they will likely have to sell at deep discounts. This will bring back memories of the global financial crisis of 2007-09. But there are reasons to think history is not about to repeat itself. First, commercial property is worth just half as much as residential real estate, which is where problems began last time around. Second, lax lending saw banks grant mortgages worth as much as 100% of a home’s value before the financial crisis. Commercial-property lenders offer a borrower a maximum 75% mortgage, meaning prices will have to fall much further for banks to face losses. ...
Look out the windows of The Economist’s office in Washington and on any given weekday a handful of builders are busy converting the old Vanguard building, an office that once housed the Peace Corps, into a block of shiny new apartments
...banks simply "declared that they intended to hold on to large portions of their money-losing bonds until they matured rather than selling them, and they then changed the bonds’ accounting labels accordingly. ... excluding the unrealized losses from their balance sheets allowed them to report robust levels of capital when in reality their assets were worth much less.If we are going to insure deposits, we need regulators to do their jobs. They can start by reading Chapter 3 (the opportunity cost of holding a bond is what they could have earned by selling it) and Chapter 5 (the value of an asset is its discounted cash flow). This is not rocket science.
Saturday, March 25, 2023
Thursday, March 23, 2023
ChatGPT vs. Google's bard on an example of incentive misalignment, why it occurred, and how to fix it.
Please give me an real-world example of incentive misalignment, why it occurred, how to fix it how much it would cost to do so.
Wednesday, March 22, 2023
The message of chapter 1, that voluntary transactions create wealth, has longer term benefits when the transactions involve labor. As Reason points out:
"When economist Raj Chetty studied dozens of local factors that correlated with upward mobility, teenage labor force participation proved more powerful than almost any other factor, even high school drop-out rates or violent crime rates," Timothy P. Carney pointed out last week in a Washington Examiner column.
Chetty, a Harvard University economist, is better known for emphasizing the value of social capital—in particular, friendships across class lines—for boosting economic mobility. But his research indicates a strong correlation between teenage participation in the labor force and upward mobility. It's a connection that's been made multiple times in the past.Although teenage labor force participation fell from 59.3% in 1978 to 32.5% in 2014, this year it climbed to 37.5%, partly as a result of less restrictive laws.
Tuesday, March 21, 2023
Luke Froeb is an accomplished and highly experienced economist who has made significant contributions to the field of antitrust economics. He has held many important positions throughout his career, including Chief Economist at the Antitrust Division of the U.S. Department of Justice and Director of the Bureau of Economics at the Federal Trade Commission. Froeb is known for his extensive scholarship and research on competition policy, antitrust economics, and industrial organization. He has published numerous articles in top academic journals and has co-authored several highly regarded textbooks on the subject. Additionally, he has served as an expert witness in many high-profile antitrust cases. Froeb is also a respected educator, having taught at a number of universities, including Vanderbilt University where he currently serves as the William C. Oehmig Chair in Free Enterprise and Entrepreneurship. Through his teaching, research, and service, Luke Froeb has become a leading figure in the field of antitrust economics and has played a significant role in shaping antitrust policy in the United States.
Interestingly, it made up this part "co-authored several highly regarded textbooks on the subject." That is a feature, not a bug, which is a byproduct of the "noise" it adds to its answer. Without it, the writing seems seems sterile.
Monday, March 20, 2023
Competition between states for high earners has intensified (link):
...two structural changes have enhanced state tax competition. First, the 2017 Tax Cuts and Jobs Act capped the federal deduction for state and local taxes paid at $10,000, thus increasing the “felt cost” of state taxation, particularly for higher earners. A high-paid Silicon Valley engineer who could previously deduct $70,000 in California income taxes on his federal tax return can now only deduct $10,000. In short, the burden of his state-government tax policy went up, incentivizing him to find a better-managed state.
Second, the pandemic untethered a multitude of high-paid workers from a geographic location, creating the opportunity for taxpayers to move, and giving states an incentive to compete for their relocations. A 2022 McKinsey report found that 35 percent of workers were eligible for full-time remote work, including 46 percent of workers earning over $150,000. The Silicon Valley engineer who lost federal deductibility for his California income taxes in 2018 became eligible for remote work in 2021. His move to Austin, Texas, eliminated his entire state income-tax liability.
- One of the key ways in which AI will change economics education is in the automation of routine tasks. This includes grading, which can now be done much more quickly and accurately using AI algorithms. This will free up time for professors to focus on other tasks, such as developing new course materials and providing more individualized feedback to students.
- Another area where AI is likely to have a significant impact is in the personalization of learning. With AI-powered adaptive learning systems, students can receive individualized instruction tailored to their specific needs and learning styles. These systems can adjust the difficulty and pace of instruction based on the student’s progress and provide targeted feedback to help them improve their understanding of key concepts.
- Moreover, AI can provide students with access to vast amounts of data and information that would be otherwise difficult to process. This includes live economic data and simulations of economic models that can help students understand complex economic theories and their real-world applications.
- One of the most exciting aspects of AI in education is the potential for new modes of learning, such as gamification and virtual reality. Gamification can make economics concepts more engaging and interactive, while virtual reality can provide students with immersive experiences that allow them to explore economic phenomena in a more dynamic way.
- Finally, AI can facilitate new forms of collaboration and peer-to-peer learning. With AI-powered chatbots and social learning platforms, students can connect with each other to discuss economics concepts and receive feedback on their work. They can also collaborate on projects and assignments, sharing their knowledge and expertise to solve complex economic problems.
First, LLMs can be used to create personalized learning experiences for students. For example, an LLM could be used to create a customized study plan for a student based on their individual strengths and weaknesses. This would allow students to learn at their own pace and focus on the areas where they need the most help.
Second, LLMs can be used to provide students with real-world examples of economic concepts. For example, an LLM could be used to show students how the principles of supply and demand can be applied to the current housing market. This would help students to understand economic concepts in a more concrete way.
Third, LLMs can be used to automate tasks that are currently done by teachers. For example, an LLM could be used to grade homework assignments or create practice tests. This would free up teachers to spend more time on tasks that require human judgment, such as providing feedback to students or developing new lesson plans.
Fourth, LLMs can be used to create new forms of economic education. For example, an LLM could be used to create a virtual economy that students could explore. This would allow students to learn about economic concepts in a more hands-on way.
Overall, LLMs have the potential to revolutionize the teaching of economics. By providing personalized learning experiences, real-world examples, and automating tasks, LLMs can help students to learn economics more effectively and efficiently.
Thursday, March 16, 2023
Fortune Magazine thinks it has absorbed the lessons of chapter 1, i.e., "Make sure employees have enough information to make good decisions, and the incentive to do so."
The article points to this as evidence of incentive misalignment between payers (insurance companies) and patients:
...hepatitis C can be cured 95% of the time with pills in as little as eight weeks. Yet fewer than one in three insured people diagnosed with hepatitis C receive the cure within a year of their diagnosis, according to an August report from the Centers for Disease Control.
If we can believe the CDC stats, the article implies that payers would rather stall, i.e., avoid paying $30,000 for the cure because, patients could switch suppliers. Lets do some benefit-cost analysis to check out the plausibility of this story. If the payer does not pay for the cure, it faces the risk of having to pay for treating the symptoms of the disease.From the insurer's point of view:
- Buying the pills costs $30,000, cures the patient, and there are no further costs.
- Not buying the pills risks having to treat the patient for hepatitis C which can cost 10 times as much as the pills, e.g., a liver transplant costs $500,000
- 30,000 > p*$300,000
- Bring supply chains closer to home: managers must examine risks and build strategies that are customized to the markets they serve. Risk and regulation will require keeping data and supply chains closer to home. As a result, localization will help managers protect the chains of information, design and supply.
- Operations Hedging: a process that spreads capabilities to reduce risk of disruption – will become increasingly important, in turn reducing economies of scale and increasing costs. For example, earlier this month, Apple partner Foxconn Technology Group announced plans to invest about $700 million on a new plant in India to reduce reliance on China.
- Exit high-cost areas: managers should evaluate exiting some countries due to the expense of supporting subscale operations or serving small markets. American clothing retailer Gap sold its Chinese business to Baozun, a local e-commerce company, in late 2022 after 12 years of operating in the region.
Monday, March 13, 2023
An unwillingness to guarantee all the deposits would satisfy the desire to penalize businesses and banks for their mistakes, limit moral hazard, and limit the fiscal liabilities of the public sector. ...
Once depositors are allowed to take losses, both individuals and institutions will adjust their deposit behavior, and they probably would do so relatively quickly. Smaller banks would receive many fewer deposits, and the giant “too big to fail” banks, such as JP Morgan, would receive many more deposits. ...
In essence, we would end up centralizing much of our American and foreign capital in our “too big to fail” banks. That would make them all the more too big to fail. It also might boost financial sector concentration in undesirable ways.
Update from the Economist:
Friday, March 10, 2023
...The neutral portfolio’s cumulative return (334%) outgained the market (230%); the results were substantially more compelling using equal-weighted returns as an alternative method....
One interesting result is the point at which performance notably begins deviating—2017-18, around the time companies (and perhaps their profits and returns) began feeling pressure from the power and influence of supposedly passive asset managers such as BlackRock, State Street and Vanguard, as those behemoths’ push into ESG intensified.This is a "compensating differential" from Chapter 9, albeit a negative one. In other words, you pay to invest in ESG funds. See related posts
Thursday, March 9, 2023
After a steady decline in profitability, Barnes & Noble is rebounding. It was purchased by a hedge fund in 2019 in order to implement a new strategy of more local autonomy. It turns out that book demand is quite regional and even local. The new strategy allows individual stores to make decisions on what titles to stock. They even stopped publisher promotions of potentially unpopular books in special displays.
- Who was making inventory decisions? HQ
- Did they have good incentives to make good choices? Yes
- Did they have good information on what choices to make? No
Solution: Allow at least some inventory decisions to be made at the stores who know their clientele's particular tastes. I suspect that this also required greater incentives at the store level.
Wednesday, March 8, 2023
Monday, March 6, 2023
American universities have professed allegiance to two ideals. First, the ideal of academic freedom – the right of students and faculty to express any idea in speech or writing, without fear of university punishment, and secure in the knowledge that the university will protect dissenters from threats and violence on campus.
Second, the ideal of intellectual merit – the right and duty of academic departments to hire and promote the most brilliant, creative, and productive faculty in their fields, and admit the most intellectually promising students, without pressures from the administration.
Sunday, March 5, 2023
The Economist has a nice summary of the contradictions of ESG investing:
There are plenty of problems with the esg movement. Working out if assets are esg-compliant is complex, and prone to bias, mismeasurement and public-relations peacocking. Proponents of feel-good investing want to have their cake and eat it, insisting that the focus on stakeholders is actually better for shareholders, too.But it also correctly identifies the problems with anti-ESG inveting:
At the moment, taking a position against esg is much more expensive than going with the crowd. This is particularly true when it comes to anti-esg laws, which are more preoccupied with bashing esg-promoting firms than with prioritising shareholder returns and cutting costs for taxpayers.BOTTOM LINE: letting politics interfere with inveting criteria is going to cost you.
Wednesday, March 1, 2023
And the remarkable thing is that when ChatGPT does something like write an essay what it’s essentially doing is just asking over and over again “given the text so far, what should the next word be?”—and each time adding a word. ...
But, OK, at each step it gets a list of words with probabilities. But which one should it actually pick to add to the essay (or whatever) that it’s writing? One might think it should be the “highest-ranked” word (i.e. the one to which the highest “probability” was assigned). But this is where a bit of voodoo begins to creep in. Because for some reason—that maybe one day we’ll have a scientific-style understanding of—if we always pick the highest-ranked word, we’ll typically get a very “flat” essay, that never seems to “show any creativity” (and even sometimes repeats word for word). But if sometimes (at random) we pick lower-ranked words, we get a “more interesting” essay.
The fact that there’s randomness here means that if we use the same prompt multiple times, we’re likely to get different essays each time. And, in keeping with the idea of voodoo, there’s a particular so-called “temperature” parameter that determines how often lower-ranked words will be used, and for essay generation, it turns out that a “temperature” of 0.8 seems best. ...
This is a good illustration of "randomization," the idea that sometimes the best course of action is not the one that gives you the highest expected profit, but rather some random mix of options.