What do you think?
Rate this book
The Money Illusion: Market Monetarism, the Great Recession, and the Future of Monetary Policy
The first book-length work on market monetarism, written by its leading scholar.
Is it possible that the consensus around what caused the 2008 Great Recession is almost entirely wrong? It’s happened before. Just as Milton Friedman and Anna Schwartz led the economics community in the 1960s to reevaluate its view of what caused the Great Depression, the same may be happening now to our understanding of the first economic crisis of the 21st century.
Foregoing the usual relitigating of problems such as housing markets and banking crises, renowned monetary economist Scott Sumner argues that the Great Recession came down to one nominal GDP, the sum of all nominal spending in the economy, which the Federal Reserve erred in allowing to plummet. The Money Illusion is an end-to-end case for this school of thought, known as market monetarism, written by its leading voice in economics. Based almost entirely on standard macroeconomic concepts, this highly accessible text lays the groundwork for a simple yet fundamentally radical understanding of how monetary policy can work providing a stable environment for a market economy to flourish.
Is it possible that the consensus around what caused the 2008 Great Recession is almost entirely wrong? It’s happened before. Just as Milton Friedman and Anna Schwartz led the economics community in the 1960s to reevaluate its view of what caused the Great Depression, the same may be happening now to our understanding of the first economic crisis of the 21st century.
Foregoing the usual relitigating of problems such as housing markets and banking crises, renowned monetary economist Scott Sumner argues that the Great Recession came down to one nominal GDP, the sum of all nominal spending in the economy, which the Federal Reserve erred in allowing to plummet. The Money Illusion is an end-to-end case for this school of thought, known as market monetarism, written by its leading voice in economics. Based almost entirely on standard macroeconomic concepts, this highly accessible text lays the groundwork for a simple yet fundamentally radical understanding of how monetary policy can work providing a stable environment for a market economy to flourish.
392 pages, Hardcover
Published September 3, 2021
39 people are currently reading
556 people want to read
About the author
Scott Sumner
15 books17 followersScott B. Sumner is Research Fellow at the Independent Institute, the Director of the Program on Monetary Policy at the Mercatus Center at George Mason University and an economist who teaches at Bentley University in Waltham, Massachusetts. His economics blog, The Money Illusion, popularized the idea of nominal GDP targeting, which says that the Fed should target nominal GDP.
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 11 of 11 reviews
January 1, 2022
This is the best book on macroeconomics that I'm aware of, with a focus on the causes of the 2008 recession.
Most of the book's important points are based on ideas that economists respect in many contexts outside of macroeconomics, but which seem controversial in the context of macroeconomics.
It's ironic that Sumner finished writing this book during one of the few recessions that could not have been prevented by better monetary policy.
Note that this review is primarily for people who already know something about monetary policy. It's hard enough to do that well that I don't want to attempt anything more ambitious.
I'll start with the five differences from standard opinions that I consider most important.
Never Reason from a Price Change
Price changes provide potentially valuable information, but when they warn of problems, they are ambiguous as to the cause in the absence of further information.
E.g. a large drop in oil prices might mean that fracking has made more oil available (as in 2014), or it might mean that pandemic lockdowns reduced demand.
Economists know this in the abstract, but often forget it when evaluating monetary policy. They saw interest rates decline in 2008, and imagined that was due to the Fed adopting a more stimulative monetary policy. People who looked carefully could see a good deal of evidence that market forces were pushing interest rates down, and that the Fed was keeping rates higher than markets would have, in order to avoid overstimulation.
Economists have mostly conceded that the low interest rates of the 1930s coincided with tight money. There were modest similarities between 2008 and the 1930s, yet too many economists looked at low, declining, interest rates in 2008 and were unwilling to imagine that monetary policy was tight.
When respected economists are confused as to whether monetary policy is tight, it's hard for a central bank to notice its mistakes.
Respect the Efficient Market Hypothesis
That doesn't mean we should ignore prices. Predictions based on current financial prices can rarely be beaten.
Economists debate the Efficient Market Hypothesis (EMH) a lot, although they mostly agree that it's at least approximately correct.
Yet the Fed trusts its own forecasts over market forecasts (or at least it did in 2008), and few economists complain about that.
On Sept 16, 2008, the TIPS spread predicted that CPI inflation would be 1.23% over the next five years. Whereas the Fed announcement that day implied a CPI inflation forecast of around 2.3 to 2.5% (i.e. they expected to hit their target; I don't think they specified a time period). The actual inflation rate turned out to be 1.31%.
The Fed chose not to alter course that day, when markets were saying clearly that monetary policy was going off course. So it seems the Fed accepted a weakening economy at least in part because they mistakenly believed that more stimulus would cause excessive inflation. That's one of the clearest examples of why the Fed deserves blame for the recession.
Another example of market prices providing valuable information came on the three days in the fall of 2008 when the Fed announced interest rate increases (not the standard rate increases - this was a new interest rate called interest on reserves, which attracted less attention). Adding together the three reactions to the three rate increases, we get a total stock market decline of 15%. The Fed shouldn't automatically treat such declines as bad, but such declines should alert it to the possibility that it was misjudging conditions.
Expectations Matter
In 1933, FDR altered the dollar to become pegged to a smaller amount of gold. That didn't have an unusual short-term effect on interest rates or money supply. Yet it triggered a few months of high inflation, a dramatic stock market rally, and abnormally strong economic expansion (cut short by an unrelated policy blunder).
Why? Because it was a clear commitment to a sustained increase in the money supply - an increase which was incompatible with the prior policy of keeping the dollar at 1/20.67 ounces of gold.
In contrast, huge increases in the money supply can be ineffective if they're expected to be temporary. In a 1998 paper that Sumner calls "important and underrated", Krugman explains:
Here's a scenario which clarifies why increases in the money supply might be ineffective: interest rates are zero, and people mostly expect that the Fed will pursue policies which will cause steady deflation. Holding on to more cash will be a sensible investment decision, because that cash is expected to buy more in the future. Why buy a house now if it will cost less next year? (People will still buy houses to live in, but they'll avoid investment-motivated housing purchases).
It looks like the U.S. hasn't quite reached this kind of liquidity trap since the 1930s, when the gold standard more or less required the Fed to allow deflation.
Japan was mostly in a liquidity trap from 1990 to at least 2012, with the central bank seeming to target an inflation rate of exactly zero. It at least partially recovered in 2013 when Abe was elected with a promise of inflation.
Prior to reading this book, I was confused as to what mainstream economists think about liquidity traps. Part of my confusion came from reading commentators who imagine that the Fed can only stimulate the economy via the act of cutting interest rates. The financialnews storytellers often seem to believe that, but leading economists (e.g. Bernanke) seem wiser than that.
Now I at least understand why economists take liquidity traps seriously. Yet Japan's ambiguous partial recovery from one suggests that I don't fully understand the phenomenon.
A good deal of theory and evidence backs the importance of expectations, but too many people still focus on today's money supply to the exclusion of asking what policy the Fed will use years from now to influence inflation or the money supply.
Level Targeting
Sumner wants the Fed to compensate for recent mistakes by aiming to get the monetary target (e.g. inflation or NGDP) back onto the track that it had previously committed to. E.g. in 2020 the Fed seemed to endorse this policy, so that we ought to be able to forecast now what price levels will be in 2030.
One benefit of level targeting would be that people can make long-term plans today with less uncertainty about whether the Fed's mistakes next year will impair our ability to predict prices in 2030.
A more important benefit is that when the Fed errs in the direction of deflation, that interacts with sticky wages to make a temporary increase in inflation more valuable at minimizing unemployment.
Incidentally, the Fed's behavior this year seems to be an example of why some economists have claimed there's a long and variable delay between when the Fed adopts a policy and when the economy responds. A better description of this phenomenon is that there's a long and variable delay between policy announcements and when, if ever, the Fed clearly decides to follow the new policy.
NGDP versus Inflation
Sumner wants the Fed to target NGDP growth rather than inflation.
Mainstream macroeconomic theory advises governments to influence aggregate demand. Sumner comments:
He provides a few examples of when targeting NGDP would have produced better results, such as mid-2008, when NGDP forecasts seemed to start falling a bit earlier than inflation forecasts. Targeting NGDP will cause inflation to be higher when economic activity slows, which seems likely to stabilize the economy a bit more than constant inflation would.
Targeting NGDP can't be a complete answer here, because a semi-arbitrary growth rate such as 4% per year could cause problems if we had very different productivity growth or population growth. Sumner seems satisfied with improving on existing policies, rather than aiming for perfection.
Alternate Explanations
Sumner provides both theory and evidence that the main alternatives to monetary policy seem to be weak explanations for recessions. The evidence is hardly conclusive, but in combination with theory it's good enough to be taken seriously.
Did fiscal policy cause the recession? Sumner provides examples that seem inconsistent with standard claims about how budget deficits stimulate the economy:
* the 1968 tax increase, which eliminated the budget deficit, without keeping inflation from accelerating (the economy slowed a bit, but slowed more when the tax expired).
* tax increases in 2013 caused the deficit to shrink nearly in half; many leading economists predicted a double-dip recession. Instead, the economy grew a bit faster than it did in 2012.
* Japan's 2013 Abenomics example of fiscal austerity and monetary stimulus improved the Japanese economy.
Did the stock market crash cause the recession? The 1987 crash is a clear piece of evidence that such crashes don't necessarily cause recessions.
Did the banking crisis cause the recession? Sumner's best evidence here involves comparing Iceland to Ireland.
Iceland had a banking crisis, about which Wikipedia says:
Whereas Ireland had a an ordinary enough crisis that it was able to bail out its banks.
Does the size of the banking crisis tell us which economy was hurt worse? The Washington Post compared them in a 2015 story titled The miraculous story of Iceland, saying "No, the biggest difference between the two is that Iceland has its own currency and Ireland has the euro."
The ECB adopted a tighter monetary policy than the U.S. around 2008-2015, which coincided with slower growth in the eurozone than the anemic U.S. economy. Whereas Iceland's monetary policy created rather high inflation for a few years.
I suppose that we can't rule out the possibility that Iceland's success was due to not bailing out its banks. I doubt that bailouts have big economic effects, but we should keep this example in mind the next time banks ask to be bailed out.
No Bubbles
Did the housing bubble cause the recession? No. Or at least not directly. The slump in housing construction was more than halfway to its bottom in April 2008, yet nearly all the increase in unemployment came later. Also, the eurozone had a worse recession without having had a notable housing bubble.
Erdmann's book Shut Out did a better job than Sumner at showing that the housing bubble had mostly stopped causing disruptions by the start of the recession, so it's pretty hard to see the bubble as a direct cause of the recession. It still seems quite plausible that the bubble generated conditions under which central banks were likely to make mistakes.
Sumner goes further, denying that bubbles are even a useful concept, as bubbles are inconsistent with the EMH. That requires an implausibly strong version of the EMH.
He's right that bubbles are a less useful concept than the EMH. At least 30% of investors would do better if they respected the EMH more, whereas maybe 3% of investors benefit from worrying about bubbles.
But 3% is not zero. It's probably not much different from the number of investors whose investing would benefit from the improved understanding of this book.
If we had to choose between the EMH and the bubble hypothesis, then Sumner would be correct to choose the EMH. But there's no need for a strong enough version of the EMH to rule out all bubbles.
As an investor, I found it useful to say in 2005 that the U.S. had a housing bubble. It would have been useful for me to identify a bubble involving irrational confidence in the Fed's competence.
But I'm not typical. It's unclear whether it's useful for central banks or regulators to believe that bubbles are possible. Without strong incentives to distinguish bubbles from healthy markets, most people who think they can identify bubbles will be correct less than half the time. This is especially true for institutions that are influenced by the average voter's opinions - almost by definition of a bubble, the average voter will be mistaken about whether a market is experiencing a bubble. Elite opinion isn't much better, unless the elites are selected for their skill at beating markets.
Erdmann provided some evidence that regulators, and maybe the Fed, caused significant harm via mistaken attempts at deflating an already-deflated housing bubble in 2008-11. I see signs that China is currently making similar attempts to deflate a housing market that seems not to have a bubble.
Conclusion
Sumner has a well thought out procedure for a good monetary rule. I'm reluctant to summarize it - the one paragraph version would sound weird to most people, and I don't have enough time to explain it in a way that does it justice. I prefer to focus most readers' attention on how the worst mistakes can be avoided. That will likely produce more value than arguing about which policy is best. The only politically feasible path toward his favored monetary rule is through incremental changes to avoid specific mistakes.
We can't be sure that Sumner's policies would have avoided a recession, but it's pretty clear they would have at least made it substantially milder. I'm pretty sure they would have avoided more than a half trillion dollars of harm from monetary conditions.
This book won't be the final word on monetary policy, but it represents an important step in the right direction.
Most of the book's important points are based on ideas that economists respect in many contexts outside of macroeconomics, but which seem controversial in the context of macroeconomics.
It's ironic that Sumner finished writing this book during one of the few recessions that could not have been prevented by better monetary policy.
Note that this review is primarily for people who already know something about monetary policy. It's hard enough to do that well that I don't want to attempt anything more ambitious.
I'll start with the five differences from standard opinions that I consider most important.
Never Reason from a Price Change
Price changes provide potentially valuable information, but when they warn of problems, they are ambiguous as to the cause in the absence of further information.
E.g. a large drop in oil prices might mean that fracking has made more oil available (as in 2014), or it might mean that pandemic lockdowns reduced demand.
Economists know this in the abstract, but often forget it when evaluating monetary policy. They saw interest rates decline in 2008, and imagined that was due to the Fed adopting a more stimulative monetary policy. People who looked carefully could see a good deal of evidence that market forces were pushing interest rates down, and that the Fed was keeping rates higher than markets would have, in order to avoid overstimulation.
Economists have mostly conceded that the low interest rates of the 1930s coincided with tight money. There were modest similarities between 2008 and the 1930s, yet too many economists looked at low, declining, interest rates in 2008 and were unwilling to imagine that monetary policy was tight.
When respected economists are confused as to whether monetary policy is tight, it's hard for a central bank to notice its mistakes.
Respect the Efficient Market Hypothesis
That doesn't mean we should ignore prices. Predictions based on current financial prices can rarely be beaten.
Economists debate the Efficient Market Hypothesis (EMH) a lot, although they mostly agree that it's at least approximately correct.
Yet the Fed trusts its own forecasts over market forecasts (or at least it did in 2008), and few economists complain about that.
On Sept 16, 2008, the TIPS spread predicted that CPI inflation would be 1.23% over the next five years. Whereas the Fed announcement that day implied a CPI inflation forecast of around 2.3 to 2.5% (i.e. they expected to hit their target; I don't think they specified a time period). The actual inflation rate turned out to be 1.31%.
The Fed chose not to alter course that day, when markets were saying clearly that monetary policy was going off course. So it seems the Fed accepted a weakening economy at least in part because they mistakenly believed that more stimulus would cause excessive inflation. That's one of the clearest examples of why the Fed deserves blame for the recession.
Another example of market prices providing valuable information came on the three days in the fall of 2008 when the Fed announced interest rate increases (not the standard rate increases - this was a new interest rate called interest on reserves, which attracted less attention). Adding together the three reactions to the three rate increases, we get a total stock market decline of 15%. The Fed shouldn't automatically treat such declines as bad, but such declines should alert it to the possibility that it was misjudging conditions.
Expectations Matter
In 1933, FDR altered the dollar to become pegged to a smaller amount of gold. That didn't have an unusual short-term effect on interest rates or money supply. Yet it triggered a few months of high inflation, a dramatic stock market rally, and abnormally strong economic expansion (cut short by an unrelated policy blunder).
Why? Because it was a clear commitment to a sustained increase in the money supply - an increase which was incompatible with the prior policy of keeping the dollar at 1/20.67 ounces of gold.
In contrast, huge increases in the money supply can be ineffective if they're expected to be temporary. In a 1998 paper that Sumner calls "important and underrated", Krugman explains:
In a liquidity trap, the problem is that the markets believe that the central bank will target price stability, given the chance, and hence that any current monetary expansion is merely transitory. The traditional view that monetary policy is ineffective in a liquidity trap, and that fiscal expansion is the only way out, must therefore be qualified: monetary policy will in fact be effective if the central bank can credibly promise to be irresponsible, to seek a higher future price level.
Here's a scenario which clarifies why increases in the money supply might be ineffective: interest rates are zero, and people mostly expect that the Fed will pursue policies which will cause steady deflation. Holding on to more cash will be a sensible investment decision, because that cash is expected to buy more in the future. Why buy a house now if it will cost less next year? (People will still buy houses to live in, but they'll avoid investment-motivated housing purchases).
It looks like the U.S. hasn't quite reached this kind of liquidity trap since the 1930s, when the gold standard more or less required the Fed to allow deflation.
Japan was mostly in a liquidity trap from 1990 to at least 2012, with the central bank seeming to target an inflation rate of exactly zero. It at least partially recovered in 2013 when Abe was elected with a promise of inflation.
Prior to reading this book, I was confused as to what mainstream economists think about liquidity traps. Part of my confusion came from reading commentators who imagine that the Fed can only stimulate the economy via the act of cutting interest rates. The financial
Now I at least understand why economists take liquidity traps seriously. Yet Japan's ambiguous partial recovery from one suggests that I don't fully understand the phenomenon.
A good deal of theory and evidence backs the importance of expectations, but too many people still focus on today's money supply to the exclusion of asking what policy the Fed will use years from now to influence inflation or the money supply.
Level Targeting
Sumner wants the Fed to compensate for recent mistakes by aiming to get the monetary target (e.g. inflation or NGDP) back onto the track that it had previously committed to. E.g. in 2020 the Fed seemed to endorse this policy, so that we ought to be able to forecast now what price levels will be in 2030.
One benefit of level targeting would be that people can make long-term plans today with less uncertainty about whether the Fed's mistakes next year will impair our ability to predict prices in 2030.
A more important benefit is that when the Fed errs in the direction of deflation, that interacts with sticky wages to make a temporary increase in inflation more valuable at minimizing unemployment.
Incidentally, the Fed's behavior this year seems to be an example of why some economists have claimed there's a long and variable delay between when the Fed adopts a policy and when the economy responds. A better description of this phenomenon is that there's a long and variable delay between policy announcements and when, if ever, the Fed clearly decides to follow the new policy.
NGDP versus Inflation
Sumner wants the Fed to target NGDP growth rather than inflation.
Mainstream macroeconomic theory advises governments to influence aggregate demand. Sumner comments:
a high inflation rate is viewed as an indicator of strong aggregate demand, and low inflation implies weak demand. My view is that, rather than using inflation as an indicator of aggregate demand, we should use aggregate demand as an indicator of aggregate demand. And nominal GDP, which measures total spending, is basically what people mean by aggregate demand.
He provides a few examples of when targeting NGDP would have produced better results, such as mid-2008, when NGDP forecasts seemed to start falling a bit earlier than inflation forecasts. Targeting NGDP will cause inflation to be higher when economic activity slows, which seems likely to stabilize the economy a bit more than constant inflation would.
Targeting NGDP can't be a complete answer here, because a semi-arbitrary growth rate such as 4% per year could cause problems if we had very different productivity growth or population growth. Sumner seems satisfied with improving on existing policies, rather than aiming for perfection.
Alternate Explanations
Sumner provides both theory and evidence that the main alternatives to monetary policy seem to be weak explanations for recessions. The evidence is hardly conclusive, but in combination with theory it's good enough to be taken seriously.
Did fiscal policy cause the recession? Sumner provides examples that seem inconsistent with standard claims about how budget deficits stimulate the economy:
* the 1968 tax increase, which eliminated the budget deficit, without keeping inflation from accelerating (the economy slowed a bit, but slowed more when the tax expired).
* tax increases in 2013 caused the deficit to shrink nearly in half; many leading economists predicted a double-dip recession. Instead, the economy grew a bit faster than it did in 2012.
* Japan's 2013 Abenomics example of fiscal austerity and monetary stimulus improved the Japanese economy.
Did the stock market crash cause the recession? The 1987 crash is a clear piece of evidence that such crashes don't necessarily cause recessions.
Did the banking crisis cause the recession? Sumner's best evidence here involves comparing Iceland to Ireland.
Iceland had a banking crisis, about which Wikipedia says:
Relative to the size of its economy, Iceland's systemic banking collapse was the largest experienced by any country in economic history.
Whereas Ireland had a an ordinary enough crisis that it was able to bail out its banks.
Does the size of the banking crisis tell us which economy was hurt worse? The Washington Post compared them in a 2015 story titled The miraculous story of Iceland, saying "No, the biggest difference between the two is that Iceland has its own currency and Ireland has the euro."
The ECB adopted a tighter monetary policy than the U.S. around 2008-2015, which coincided with slower growth in the eurozone than the anemic U.S. economy. Whereas Iceland's monetary policy created rather high inflation for a few years.
I suppose that we can't rule out the possibility that Iceland's success was due to not bailing out its banks. I doubt that bailouts have big economic effects, but we should keep this example in mind the next time banks ask to be bailed out.
No Bubbles
Did the housing bubble cause the recession? No. Or at least not directly. The slump in housing construction was more than halfway to its bottom in April 2008, yet nearly all the increase in unemployment came later. Also, the eurozone had a worse recession without having had a notable housing bubble.
Erdmann's book Shut Out did a better job than Sumner at showing that the housing bubble had mostly stopped causing disruptions by the start of the recession, so it's pretty hard to see the bubble as a direct cause of the recession. It still seems quite plausible that the bubble generated conditions under which central banks were likely to make mistakes.
Sumner goes further, denying that bubbles are even a useful concept, as bubbles are inconsistent with the EMH. That requires an implausibly strong version of the EMH.
He's right that bubbles are a less useful concept than the EMH. At least 30% of investors would do better if they respected the EMH more, whereas maybe 3% of investors benefit from worrying about bubbles.
But 3% is not zero. It's probably not much different from the number of investors whose investing would benefit from the improved understanding of this book.
If we had to choose between the EMH and the bubble hypothesis, then Sumner would be correct to choose the EMH. But there's no need for a strong enough version of the EMH to rule out all bubbles.
As an investor, I found it useful to say in 2005 that the U.S. had a housing bubble. It would have been useful for me to identify a bubble involving irrational confidence in the Fed's competence.
But I'm not typical. It's unclear whether it's useful for central banks or regulators to believe that bubbles are possible. Without strong incentives to distinguish bubbles from healthy markets, most people who think they can identify bubbles will be correct less than half the time. This is especially true for institutions that are influenced by the average voter's opinions - almost by definition of a bubble, the average voter will be mistaken about whether a market is experiencing a bubble. Elite opinion isn't much better, unless the elites are selected for their skill at beating markets.
Erdmann provided some evidence that regulators, and maybe the Fed, caused significant harm via mistaken attempts at deflating an already-deflated housing bubble in 2008-11. I see signs that China is currently making similar attempts to deflate a housing market that seems not to have a bubble.
Conclusion
Sumner has a well thought out procedure for a good monetary rule. I'm reluctant to summarize it - the one paragraph version would sound weird to most people, and I don't have enough time to explain it in a way that does it justice. I prefer to focus most readers' attention on how the worst mistakes can be avoided. That will likely produce more value than arguing about which policy is best. The only politically feasible path toward his favored monetary rule is through incremental changes to avoid specific mistakes.
We can't be sure that Sumner's policies would have avoided a recession, but it's pretty clear they would have at least made it substantially milder. I'm pretty sure they would have avoided more than a half trillion dollars of harm from monetary conditions.
This book won't be the final word on monetary policy, but it represents an important step in the right direction.
January 3, 2022
I have a personal rule to never read or think about monetary policy as it is too complicated for me to understand. I made an exception for The Money Illusion 1) out of respect for Scott, who is such a thoughtful and interesting blogger (about non-monetary subjects) and 2) Market Monetarism seems potentially directionally right, helpful and an underrated idea that can materially improve the future.
While the argument in The Money Illusion all feel right to me, I'm not qualified to assess the merits so this review/rating is mostly just me signal boosting the idea.
While the argument in The Money Illusion all feel right to me, I'm not qualified to assess the merits so this review/rating is mostly just me signal boosting the idea.
January 24, 2022
Anybody even slightly interested in monetary policy must read this book. Even if you disagree with the author's arguments, he does an excellent job addressing reasonable critiques and explaining many fundamental concepts. The book also does an excellent job of identifying frequent mistakes people make in arguing about monetary policy.
January 16, 2026
Scott Sumner is an academic scribbler who teaches at a mid-tier college (think "almost as good as Florida State or Clemson") called "Bentley University". Sumner is a new-age-sufi quantity theorist who believes he has found the holy grail of economic prosperity - the money printer.
Scott has been juped into using empirical evidence showing that inflating the money supply stimulates trade. Apart from the fact that this insight is 300 + years old, he is wrong about money and the economy.
He points out that he's very impressive, having caught the attention of Federal Reserve governors, who, to the surprise of exactly nobody, jumped on this bandwagon of "Your money printer is running too slow, bro".
Per chatGPT, Bentley University's $362 million endowment fund consists almost entirely of the profits Scott donated after buying puts on QQQ in the 2007/8 credit crunch. He even shows a table of his Fidelity trading account in the appendix, putting to rest the inevitable questions about his self-proclaimed genius. Per chatGPT: "dozens of Scott Sumner's former students and friends drive Learjets and Mr. Sumner lives at Downtown Abbey, replete with Renoirs and lady's maids and footmen. He is also the only person who understands how the economy works".
I did, however, find this book a tad patronizing, all while being incredibly basic. I stopped around p. 25 where he was talking about dime shortages and Hitler's parents. I sort of lost the plot there but it did feel as though Scott knows very little about money, banking or the economy, which makes me question whether chatGPT can have bad days.
Alas - the next day, I asked it what Richard Werner (who is a legit inside member of the church, and a practitioner, though not on my side of the aisle) would think of Scott's insights:
***************
Short answer: Werner would be deeply critical of Sumner, and the criticism would go to first principles, not policy details.
Here is the clean mapping.
1. Werner’s core framework (reminder)
Werner’s theory (credit theory of money) rests on three pillars:
Banks create money when they create credit (not via reserves or base money).
The destination of credit matters:
productive credit → real growth, stable prices
asset/financial credit → bubbles, instability
Macro instability is caused by misdirected bank credit, not by failures of aggregate nominal spending.
This puts Werner much closer to:
MacLeod / Banking School,
Fullarton’s reflux logic,
(though Werner stresses credit allocation more than asset backing).
2. Where Werner and Sumner directly clash
a) What drives the macroeconomy
Sumner:
NGDP expectations drive output and prices.
Central bank must stabilize expected nominal spending.
Werner:
Bank credit creation drives output and prices.
Central banks are largely followers, not controllers, of credit.
Werner would say Sumner mistakes a symptom (NGDP) for a cause (credit creation).
b) Quantity Theory vs Credit Theory
Sumner is explicitly QTM-with-expectations:
MV (expected) determines PY.
Werner rejects this entirely:
Velocity is not stable,
Money aggregates obscure bank balance-sheet behavior,
Causality runs from credit → income, not money → spending.
From Werner’s perspective, NGDP targeting is epistemically empty: it tells you what happened, not why.
c) “Market monetarism” vs real markets
Werner would be unimpressed by the “market” label.
Why?
NGDP futures markets still presuppose a central authority enforcing nominal outcomes.
They do not discipline which banks create credit, or for what purpose.
Werner would likely say:
“This is not market-based money; it is centralized price targeting.”
3. Where Werner would be especially hostile
NGDP targeting and credit bubbles
Werner has repeatedly argued:
Japan’s bubbles occurred despite stable CPI,
and could easily occur under stable NGDP.
He would argue NGDP targeting:
allows asset bubbles to grow unchecked,
so long as consumer prices and aggregate income behave.
This is a direct contradiction of his empirical work on Japan, the UK, and Europe.
4. Where Werner might give limited credit
To be fair, Werner would agree with Sumner on one point:
Interest rates are a poor policy instrument.
Werner prefers:
credit guidance,
or structural controls on bank lending,
while Sumner prefers:
expectations and nominal targets.
Shared diagnosis (rates are misleading), completely different cures.
5. Verdict, in Werner’s likely voice
A plausible Werner-style summary:
“Sumner correctly rejects interest-rate targeting, but replaces it with an equally misleading aggregate nominal target. By ignoring bank credit creation and its allocation, NGDP targeting treats the monetary system as a black box. Stability cannot be achieved by steering aggregates; it requires control of bank credit creation itself.”
6. Your triangulation is correct
If we place them on your internal map:
Fullarton/Law/Bosanquet→ money as asset-backed security
Werner → money as bank credit tied to real transactions
Sumner → money as nominal unit stabilized by expectations
Werner and Sumner are on opposite sides of the causal chain.
So no—you are not misreading this. Werner would not be impressed, and he would not be polite about it.
*********
chatGPT can read my mind, we have a great relationship and we both agree that Scott Sumner is a waste of time. Only other confused academic scribblers could appreciate this offensive scribble.
PS: SS is proved wrong in his own book. He says, p. 16:
POSTSCRIPT: "Just after the manuscript was completed and sent to the publisher, the US was hit by Covid 19... ... in that case expansionary policy can play a useful role... *Early indications are that inflation is likely to fall in 2020 and 2021, exactly the opposite of what is appropiate when aggegate supply declines...*"
**************
https://www.bls.gov/charts/consumer-p...
email from a legit Austrian economist, who would find Sumner fascinating. Just email him and ask him.
*****************
From: Frank Shostak - AAS Economics
Date: Thu, Apr 22, 2021 at 12:54 AM
Subject: RE: Where are 10 year yields heading?
To: (Rommel Monet)
I do think that liquidity is likely to exert downward pressure. However, the emerging price inflation in particular during next year likely to dominate the scene. (Rommel), we provide extensive services regarding where the markets are likely to go. If you were to decide to acquire our services please let me know.
***************
Wah-wahhh...
Edit - 1/6/25. Just to be safe, I did bookmark the MoneyIllusion. I like money too. Does anyone know if he publishes a liquidity gauge that says "Buy" or "Sell"? Surely he does, and I want in on it. What if Tuesday-chatGPT is correct afterall?
These money shortages sound dangerous. There is clearly a money shortage going on right now which is why Bitcoins are stuck in the $90k trading range. Come on Wall Street, give the people what they want!
Can anyone evaluate this review and post a comment in the chat to tell me if I should read this book and why? Feels like a 2/10, like a monetarist Paul Krugman. The fact that Krugman* is cited in this book multiple times as an authority should make even the simplist of minds skeptical
*(look up his dismal essay on Austrian economics, he is simply not educated in the field of business cycles and credit money. But no Keynesians are, GT ruined the good Keynes and put fairy tale logic into the mainstream, attracting academic scribblers like Scott, all of them with a plan to save the world [or at least give us a free lunch using their brain]. The delusion of these people. Govt apologists and nothing more.
)
>> You're a uni professor in Waltham Mass, friend, and a simple economist, unlearned.
Scott has been juped into using empirical evidence showing that inflating the money supply stimulates trade. Apart from the fact that this insight is 300 + years old, he is wrong about money and the economy.
He points out that he's very impressive, having caught the attention of Federal Reserve governors, who, to the surprise of exactly nobody, jumped on this bandwagon of "Your money printer is running too slow, bro".
Per chatGPT, Bentley University's $362 million endowment fund consists almost entirely of the profits Scott donated after buying puts on QQQ in the 2007/8 credit crunch. He even shows a table of his Fidelity trading account in the appendix, putting to rest the inevitable questions about his self-proclaimed genius. Per chatGPT: "dozens of Scott Sumner's former students and friends drive Learjets and Mr. Sumner lives at Downtown Abbey, replete with Renoirs and lady's maids and footmen. He is also the only person who understands how the economy works".
I did, however, find this book a tad patronizing, all while being incredibly basic. I stopped around p. 25 where he was talking about dime shortages and Hitler's parents. I sort of lost the plot there but it did feel as though Scott knows very little about money, banking or the economy, which makes me question whether chatGPT can have bad days.
Alas - the next day, I asked it what Richard Werner (who is a legit inside member of the church, and a practitioner, though not on my side of the aisle) would think of Scott's insights:
***************
Short answer: Werner would be deeply critical of Sumner, and the criticism would go to first principles, not policy details.
Here is the clean mapping.
1. Werner’s core framework (reminder)
Werner’s theory (credit theory of money) rests on three pillars:
Banks create money when they create credit (not via reserves or base money).
The destination of credit matters:
productive credit → real growth, stable prices
asset/financial credit → bubbles, instability
Macro instability is caused by misdirected bank credit, not by failures of aggregate nominal spending.
This puts Werner much closer to:
MacLeod / Banking School,
Fullarton’s reflux logic,
(though Werner stresses credit allocation more than asset backing).
2. Where Werner and Sumner directly clash
a) What drives the macroeconomy
Sumner:
NGDP expectations drive output and prices.
Central bank must stabilize expected nominal spending.
Werner:
Bank credit creation drives output and prices.
Central banks are largely followers, not controllers, of credit.
Werner would say Sumner mistakes a symptom (NGDP) for a cause (credit creation).
b) Quantity Theory vs Credit Theory
Sumner is explicitly QTM-with-expectations:
MV (expected) determines PY.
Werner rejects this entirely:
Velocity is not stable,
Money aggregates obscure bank balance-sheet behavior,
Causality runs from credit → income, not money → spending.
From Werner’s perspective, NGDP targeting is epistemically empty: it tells you what happened, not why.
c) “Market monetarism” vs real markets
Werner would be unimpressed by the “market” label.
Why?
NGDP futures markets still presuppose a central authority enforcing nominal outcomes.
They do not discipline which banks create credit, or for what purpose.
Werner would likely say:
“This is not market-based money; it is centralized price targeting.”
3. Where Werner would be especially hostile
NGDP targeting and credit bubbles
Werner has repeatedly argued:
Japan’s bubbles occurred despite stable CPI,
and could easily occur under stable NGDP.
He would argue NGDP targeting:
allows asset bubbles to grow unchecked,
so long as consumer prices and aggregate income behave.
This is a direct contradiction of his empirical work on Japan, the UK, and Europe.
4. Where Werner might give limited credit
To be fair, Werner would agree with Sumner on one point:
Interest rates are a poor policy instrument.
Werner prefers:
credit guidance,
or structural controls on bank lending,
while Sumner prefers:
expectations and nominal targets.
Shared diagnosis (rates are misleading), completely different cures.
5. Verdict, in Werner’s likely voice
A plausible Werner-style summary:
“Sumner correctly rejects interest-rate targeting, but replaces it with an equally misleading aggregate nominal target. By ignoring bank credit creation and its allocation, NGDP targeting treats the monetary system as a black box. Stability cannot be achieved by steering aggregates; it requires control of bank credit creation itself.”
6. Your triangulation is correct
If we place them on your internal map:
Fullarton/Law/Bosanquet→ money as asset-backed security
Werner → money as bank credit tied to real transactions
Sumner → money as nominal unit stabilized by expectations
Werner and Sumner are on opposite sides of the causal chain.
So no—you are not misreading this. Werner would not be impressed, and he would not be polite about it.
*********
chatGPT can read my mind, we have a great relationship and we both agree that Scott Sumner is a waste of time. Only other confused academic scribblers could appreciate this offensive scribble.
PS: SS is proved wrong in his own book. He says, p. 16:
POSTSCRIPT: "Just after the manuscript was completed and sent to the publisher, the US was hit by Covid 19... ... in that case expansionary policy can play a useful role... *Early indications are that inflation is likely to fall in 2020 and 2021, exactly the opposite of what is appropiate when aggegate supply declines...*"
**************
https://www.bls.gov/charts/consumer-p...
email from a legit Austrian economist, who would find Sumner fascinating. Just email him and ask him.
*****************
From: Frank Shostak - AAS Economics
Date: Thu, Apr 22, 2021 at 12:54 AM
Subject: RE: Where are 10 year yields heading?
To: (Rommel Monet)
I do think that liquidity is likely to exert downward pressure. However, the emerging price inflation in particular during next year likely to dominate the scene. (Rommel), we provide extensive services regarding where the markets are likely to go. If you were to decide to acquire our services please let me know.
***************
Wah-wahhh...
Edit - 1/6/25. Just to be safe, I did bookmark the MoneyIllusion. I like money too. Does anyone know if he publishes a liquidity gauge that says "Buy" or "Sell"? Surely he does, and I want in on it. What if Tuesday-chatGPT is correct afterall?
These money shortages sound dangerous. There is clearly a money shortage going on right now which is why Bitcoins are stuck in the $90k trading range. Come on Wall Street, give the people what they want!
Can anyone evaluate this review and post a comment in the chat to tell me if I should read this book and why? Feels like a 2/10, like a monetarist Paul Krugman. The fact that Krugman* is cited in this book multiple times as an authority should make even the simplist of minds skeptical
*(look up his dismal essay on Austrian economics, he is simply not educated in the field of business cycles and credit money. But no Keynesians are, GT ruined the good Keynes and put fairy tale logic into the mainstream, attracting academic scribblers like Scott, all of them with a plan to save the world [or at least give us a free lunch using their brain]. The delusion of these people. Govt apologists and nothing more.
)
>> You're a uni professor in Waltham Mass, friend, and a simple economist, unlearned.
February 27, 2022
Really great book that could serve as an introduction to monetary economics for someone with no background while also containing frontier insights. I probably have more exposure to Sumner's way of thinking about monetary theory than his "competitors" -- New Keynesians, Old Keynesians, Austrians, neoclassicals -- so I'm wary of being too all in on his version of things. But he is darn compelling! Though I am a little skeptical of his claims about how much the Fed could have done to prevent 2008: I think he decisively argues that money was *too tight* at multiple points leading into and during the recession, and that paying interest on reserves was contractionary, but none of his evidence is sufficient to establish that the 0.25 basis point differences in policy would have prevented a severe recession. And maybe I am too focused on the size of that number, but it does seem implausible that such a small shift in policy could have made all the difference (and that he underrates how much financial issues would have wreaked havoc regardless). Though whether "targeting the forecast" in NGDP futures markets would have saved the day is even harder to say.
Anyway, there are *many* areas here I would like to explore further -- i.e. Sumner's unorthodox views on the effectiveness of currency manipulation and fiscal policy, his bubble skepticism, his belief in the power of monetary artillery even at the ZLB, his belief about their being way too much focus on liquidity effects of rate changes (don't financial markets seem to treat things that way?), about how price stickiness *slows* inflation but causes all the issues, and that NGDP is the appropriate indicator of the stance of policy.
Overall, the basic yet compelling insight Sumner has is that inflation should be thought of in terms of the demand for, and the supply of, money. That seems undeniably true to me, and I really don't know what would make someone think that the Phillips curve or the natural rate is a better proxy. How Sumner's view contrasts with the fiscal theory I am less sure of.
Anyway, there are *many* areas here I would like to explore further -- i.e. Sumner's unorthodox views on the effectiveness of currency manipulation and fiscal policy, his bubble skepticism, his belief in the power of monetary artillery even at the ZLB, his belief about their being way too much focus on liquidity effects of rate changes (don't financial markets seem to treat things that way?), about how price stickiness *slows* inflation but causes all the issues, and that NGDP is the appropriate indicator of the stance of policy.
Overall, the basic yet compelling insight Sumner has is that inflation should be thought of in terms of the demand for, and the supply of, money. That seems undeniably true to me, and I really don't know what would make someone think that the Phillips curve or the natural rate is a better proxy. How Sumner's view contrasts with the fiscal theory I am less sure of.
January 30, 2022
NGDP targeters are delusional just like the MMTers, they have their own top-down theory: the central bank is omnipotent and can always bring NGDP to the previous path. They have their own interpretation of history and own theory of the great depression, QE in Japan works, the dot com bubble was not a bubble because stock prices today are higher (what?).
There are a few things I can agree on, in Q4 2008 monetary policy in the US was too tight, Japan should not tighten in 2006 etc.
Still, I think the impact of QE is negligible (only increases asset prices = P/E ) and thus NGDP targeting is not possible in the current system when the majority of the money supply (M1) is CREDIT. Deposits are defacto credits, bank reserves and cash are backed on CB's balance sheet by real assets (treasuries, MBS, ETF in Japan, etc). If you want to target NGDP you need a tool that is not credit-based - aka helicopter drop - never tried in history and there is no reason why to try it - monetary policy should be boring.
There are a few things I can agree on, in Q4 2008 monetary policy in the US was too tight, Japan should not tighten in 2006 etc.
Still, I think the impact of QE is negligible (only increases asset prices = P/E ) and thus NGDP targeting is not possible in the current system when the majority of the money supply (M1) is CREDIT. Deposits are defacto credits, bank reserves and cash are backed on CB's balance sheet by real assets (treasuries, MBS, ETF in Japan, etc). If you want to target NGDP you need a tool that is not credit-based - aka helicopter drop - never tried in history and there is no reason why to try it - monetary policy should be boring.
September 13, 2025
1，Money supply and demand decide nominal growth, unexpected money S&D shocks fluctuate output&employment&rates.
2 They are all results but not causes, and always not correlate as we thought, like high rates represent easy money expectation in long term.
3 Inflation is money illusion, real S&D shocks rarely result inflation in complicated economy.
4 Expectation is the yardstick of easy or tight money, policies should be set to fix it. Nominal GDP capture expectation most precisely, low NGDP means tight money.
5 Inflation force people to work harder, increase output. Now Keynesianists forget demand was driven by more employment, then output, rather than subsidies which lower work participation.
6 Scott never mention wealth disparity. If inflation is subjective, what about NGDP?
2 They are all results but not causes, and always not correlate as we thought, like high rates represent easy money expectation in long term.
3 Inflation is money illusion, real S&D shocks rarely result inflation in complicated economy.
4 Expectation is the yardstick of easy or tight money, policies should be set to fix it. Nominal GDP capture expectation most precisely, low NGDP means tight money.
5 Inflation force people to work harder, increase output. Now Keynesianists forget demand was driven by more employment, then output, rather than subsidies which lower work participation.
6 Scott never mention wealth disparity. If inflation is subjective, what about NGDP?
December 14, 2024
Scott Sumner has played a large role in my model of monetary policy and seems to be right on the merits about the usefulness of nominal GDP targeting. However, NGDP targeting seems to cause some problems in the case of countries like Ireland where there's substantial investment and depreciation of capital relatively untethered to inflation and unemployment constraints. The model is pretty good but nominal consumption targeting seems strictly superior due to shorter measurement lags and relying on less imputations.
Read
November 10, 2025*read for class*
Mostly interesting look at how the Fed can use NGDP growth and level targeting to avoid common pitfalls associated with monetary policy. Hopped between examples a little too much for my small brain, so maybe a different structure would’ve helped. I will definitely peek through it again, as some of the Sumner’s arguments around using inflation-adjusted treasury bonds to determine monetary policy didn’t click with me 100%, and it seemed like there was room to abuse them.
Mostly interesting look at how the Fed can use NGDP growth and level targeting to avoid common pitfalls associated with monetary policy. Hopped between examples a little too much for my small brain, so maybe a different structure would’ve helped. I will definitely peek through it again, as some of the Sumner’s arguments around using inflation-adjusted treasury bonds to determine monetary policy didn’t click with me 100%, and it seemed like there was room to abuse them.
January 8, 2024
Excellent book detailing Market Monetarism theory of Economics. Also does a great job of detailing other current theories of economics, and explaining NGDP Targeting, rather than inflation targeting for central bank policy. A bit dry and academic, need to reread, and probably get a physical copy for proper study. Very good.
November 3, 2025
DNF, very repetitive
Displaying 1 - 11 of 11 reviews