Tuesday, May 16, 2023

Hoover Monetary Policy Conference

Friday May 12 we had the annual Hoover monetary policy conference. Hoover twitter stream here.  Conference webpage and schedule here (update 5/24 now contains videos.) As before, the talks, panels, and comments will eventually be written and published. 

The Fed has experienced two dramatic institutional failures: Inflation peaking at 8%, and a rash of bank failures. There were panels focused on each, and much surrounding discussion.  

We started with a little celebration of the 30th anniversary of Taylor (1993), which put the Taylor rule on the map. As Andy Levin pointed out in the discussion, academic immortality comes when they omit the number after your name. Rich Clarida, Volker Weiland and I quickly outlined some academic influence. John Lipsky added some very interesting commentary on how the Taylor rule was important on Wall Street, and specifically from his experience at Salomon Bros. 

The second panel on financial regulation was a smash. Anat Admati chaired, with presentations by Darrell Duffie, Randy Quarles, and Amit Seru. 

Duffie showed how online banking has taken over, and the combination of twitter and online banking makes runs happen much faster than before. You don't have to stand in line, you can all push "withdraw" at once. He also showed a glaring hole in liquidity regulations: A bank cannot count as liquidity its ability to use the discount window at the Fed. 

Seru covered some of his recent work, showing just how many banks have lost 10% or more of their asset value, and thus the value of their equity. (Nobody mentioned commercial real estate, the next shoe to drop.) They gently disagreed, Darrel viewing more liquidity and better liquidity rules as the main solution, and Amit more equity. All seemed to agree that the current regulatory mechanism is fundamentally broken. 

Randy gave a thoughtful, eloquent, and impassioned talk laying to rest the common notion that "deregulation" caused SVB to fail. It would have passed all the stress tests. This will be important to read when the papers are all available. I take the implication that the regulatory structure is, again, fundamentally broken. No, more of the current regulations would not have helped. But Randy didn't say that. 

Peter Henry next presented "Disinflation and the Stock Market: Third World Lessons for First World Monetary Policy" (a paper with Anusha Chari), discussed by Josh Rauh and Chaired by Bill Nelson. A key innovation, they use stock market reactions to measure whether disinflations are a success on a cost/benefit basis. Large inflations seem to end with stock market expansions. Moderate disinflations don't really do much for stock markets. Most disinflationary reforms fail.

Over lunch, Haruhiko Kuroda, Former Governor, Bank of Japan updated us on the Japanese situation. He is confident 2% inflation will return soon. 

Niall Ferguson and Paul Schmelzing presented "The Safety Net: Central Bank Balance Sheets and Financial Crises 1587-2020," (with Martin Kornejew and Moritz Schularick), with Barry Eichengreen discussing and Michael Bordo chair. A taste: 

The paper concludes that lender of last resort operations do work, and also create moral hazard. Barry had an eloquent discussion, noting among other things that not all balance sheet expansions are the same. Look for those in the written versions. 

Next, Mickey Levy presented The Fed: Bad Forecasts and Misguided Monetary Policy, Steve Davis discussing and  Jim Wilcox chair. The Fed -- and most industry analysts -- completely missed 8% inflation, both ahead of time and as it was happening. Why? How can the Fed do better? (And why is the Fed not asking this question?) 

To me, it looks like the forecast is not much more than an AR(1) reversion to 2% inflation. The paper has a good summary of how Fed forecasts are made, along with recommendations for institutional improvement.  

Steve Davis had an excellent discussion, pointing to a central incentive problem. The Fed uses forecasts to try to shape expectations. Like pubic health authorities, it can be afraid to reveal actual fears. I also see conceptual flaws -- not much attention to supply or fiscal policy, using the Phillips curve as a causal model and as a model in itself, too much attention to the one-period link from expected inflation to inflation, and too much attention to the forecast rather than risk management; what do we do if things come out differently. 

The conference day ended with the traditional policy panel, with Jim Bullard (talk here), Philip Jefferson (talk here), Jeff Lacker, and Charlie Plosser, Chaired by John Taylor. 

Bullard pointed to the huge fiscal stimulus as a source of inflation, warming my heart. He opined that this stimulus is fading, making him hopeful for a soft landing. He presented the following chart. 

This is a very interesting measure of how much "stimulus" is sitting out there in the economy. The government did write a lot of checks, that went straight to people's bank accounts, and eventually were spent, driving up inflation. On the other hand, I am still a bit shocked that we're running $1 trillion deficit despite beyond-full employment and output revving at every bit that the "supply" side of the economy can produce. What's your measure of fiscal stimulus? Which forecasts inflation? This is a very provocative and interesting idea. 

Jefferson gave a great talk. He has the measured cadence of a seasoned central banker, but speaks very clearly and directly.  He started by announcing his appointment as vice-chair, which got a well deserved ovation. He then jumped right in: 
The title of the conference "How to Get Back on Track: A Policy Conference" is potent. Its intent and ambiguity are striking. First, the title presupposes that U.S. monetary policy is currently on the wrong track. Second, the webpage for this conference advances a puzzling definition of the phrase "on track." How so? According to the Hoover webpage, "A key goal of the conference is to examine how to get back on track and, thereby, how to reduce the inflation rate without slowing down economic growth" (emphasis added).1 As this audience knows, there are macroeconomic models that permit disinflation with no slowdown in economic growth, but the assumptions underlying these models are very strong. It's not clear, at least to me, why such a strict metric would be used to assess real-world monetary policymaking....

I loved this. It shows he took the time to read up on the conference, and I love seeing basic premises challenged. Later, this struck me as thoughtful: 

I want to share with you a few strategic principles that are important to me. First, policymakers should be ready to react to a wide range of economic conditions with respect to inflation, unemployment, economic growth, and financial stability. The unprecedented pandemic shock is a good reminder that under extraordinary circumstances it will be difficult to formulate precise forecasts in real time. Our dual mandate from the Congress is especially helpful here. It provides the foundation for all our policy decisions. Second, policymakers should clearly communicate monetary policy decisions to the public. Our commitment to transparency should be evident to the public, and monetary policy should be conducted in a way that anchors longer-term inflation expectations. Third—and this is where I am revealing my passion for econometrics—policymakers should continuously update their priors about how the economy works as new data become available. In other words, it is appropriate to change one's perspective as new facts emerge. In this sense, I am in favor of a Bayesian approach to information processing.

The first point brings us back to the problem that the Fed has so far been too silent about: How did it miss 8% inflation? And how to operate when such huge misses are possible? The Fed seems to have been making a forecast, then announcing a policy path that works for the forecast, and then trying to stick to it. In this first principle you see a quite different view. Let's call it data-dependent rather than time-dependent. 

This is a conference about the Taylor rule. Should the Fed look at more than inflation and employment? Well, yes and no according to these comments. And when models are not certain, distrust and update.

Plosser and Lacker previewed an upcoming paper on the Fed's deviation from rules. Stay tuned. 

The evening started with a delightful speech by Sebastian Edwards on Latin American inflation. Stay tuned for that too. 

Videos should be up soon, and written versions as fast as we can get authors to turn them in. This is just a teaser!  

Update: Videos are now up, with some more commentary here.


  1. It seems the Fed saw hints of inflation, hence FAIT which few understood what that really meant. But it did convey to some and I for one that the Fed did signs of inflation, how hot it would get perhaps an open question, but nevertheless they did see signs. More than likely they felt it would be mild and should I say "transitory". To me at least, it appeared the Fed was afraid of addressing the start of the boiling pot for fear of doing so might cause a recession. Human behavior and fear of upsetting a perceived steady state of things.

  2. A "Taylor Rule" can be found by optimizing (i.e., minimizing) a quadratic cost function subject to linear Euler conditions. The summand (or, integrand) of the cost function is of the form ½·[ x²(t) + Θ·π²(t)]. The Euler conditions are of the form of the NK-IS and NK-PC equations of the 2-equation NK-DSGE model, e.g., x(t) = 𝔼ₜ{x(t+1)} – σ·[ i(t) – 𝔼ₜ{π(t+1)} + ln(β)] and π(t) = β·𝔼ₜ{π(t+1)} + κ·x(t).

    To simplify the analysis, set 𝔼ₜ{x(t+1)} = x(t), and 𝔼ₜ{π(t+1)} = π(t), i.e., assume Martingale measures, and denote i(t) as the exogenous control variable (manipulated variable). A Taylor Rule is found which reduces π(t) when 𝔼ₜ{x(t+1)} and 𝔼ₜ{π(t+1)} are exogenous inputs. The algorithm avoids having to solve an arithmetic Riccati equation backwards in time from the terminal point. The Taylor Rule so found can then be applied to the time-dependent two-point boundary value problem.

  3. Reading the WSJ's article about Gensler's reservation around generative AI and systemic risk arising from uses to which generative AI could be put in the financial markets. Decided to explore Bing's generative AI app by searching for information relating to the Taylor Rule. This is the result with the query request shown at the top. As you see, Bing's version of the generative AI engine returns a plausible source-documented answer.

    Quaere: Search for: Taylor Rule for the new Keynesian dynamic stochastic general equilibrium model

    "The Taylor rule is a monetary policy guideline that stipulates how central banks should adjust interest rates in response to changes in inflation, output, or other economic conditions. The New Keynesian Dynamic Stochastic General Equilibrium (DSGE) model is a macroeconomic model that incorporates the Taylor rule as a key component³.

    "The Taylor rule in the New Keynesian DSGE model is specified as follows¹:
    R_t = ψ_3 R_{t-1} + (1 - ψ_3) [ R^* + ψ_1 (E_{t-1} π_t - π^*) - ψ_2 (E_{t-1} u_t - u^*)] + ε_TR,t
    where `R_t` is the nominal interest rate at time `t`, `R^*` is the steady-state nominal interest rate, `π_t` is inflation at time `t`, `π^*` is the steady-state inflation rate, `u_t` is the output gap at time `t`, `u^*` is the steady-state output gap, and `ε_TR,t` is a normal shock¹.

    "I hope this helps. Let me know if you have any other questions."

    Source: Conversation with Bing, 2023-05-17
    (1) The New Keynesian Dynamic Stochastic General Equilibrium Model. http://faculty.cas.usf.edu/jkwilde/macro208/Lecture%2020.pdf.
    (2) Investment and the Taylor rule in a dynamic Keynesian model. https://bing.com/search?q=Taylor+Rule+for+the+new+Keynesian+dynamic+stochastic+general+equilibrium+model.
    (3) Investment and the Taylor rule in a dynamic Keynesian model. https://www.sciencedirect.com/science/article/pii/S0165188910001272.
    (4) Some Unconventional Properties of New Keynesian DSGE Models. https://link.springer.com/article/10.1007/s10645-023-09420-4.
    (5) The New Keynesian Approach to Dynamic General Equilibrium Modeling .... https://www.sciencedirect.com/science/article/pii/B9780444595683000225.
    (6) The Role of Money in the Monetary Policy: A New Keynesian and New .... https://www.emerald.com/insight/content/doi/10.1108/S1571-03862021000029A018/full/html.

  4. One further example - this one relates to the fiscal theory of the price level. It illustrates the competitive advantages that advances that generative AI in a search engine have over a generic text search engine. The list of references is small, however it samples publications of the proponents and critics of the theory. Your recently published text book is included as the fourth cited reference.

    Quaere: Search: Economic model of the fiscal theory of the price level
    “The Fiscal Theory of the Price Level (FTPL) is a theoretical framework that explains how monetary and fiscal policies interact in the determination of macroeconomic outcomes. It suggests that government fiscal policy, including debt and taxes present and future, is the primary determinant of the price level or inflation as opposed to monetary theory¹. The key insight is that future fiscal conditions determine the current price level, whereby monetary and fiscal policy are connected by the government budget constraint¹.

    “I hope this helps. Let me know if you have any other questions.”

    Source: Conversation with Bing, 2023-05-17
    (1) Inflation and the Fiscal Theory of the Price Level | Richmond Fed. https://www.richmondfed.org/publications/research/economic_brief/2022/eb_22-39.
    (2) Fiscal theory of the price level - Wikipedia. https://en.wikipedia.org/wiki/Fiscal_theory_of_the_price_level.
    (3) Fiscal Theory of the Price Level: A Critique | The Economic Journal .... https://academic.oup.com/ej/article-abstract/112/481/459/5085401.
    (4) The Fiscal Theory of the Price Level | Princeton University Press. https://press.princeton.edu/books/hardcover/9780691242248/the-fiscal-theory-of-the-price-level.


Comments are welcome. Keep it short, polite, and on topic.

Thanks to a few abusers I am now moderating comments. I welcome thoughtful disagreement. I will block comments with insulting or abusive language. I'm also blocking totally inane comments. Try to make some sense. I am much more likely to allow critical comments if you have the honesty and courage to use your real name.