The following is taken from a comment on my previous post. I guess the election doesn't mean we are out of the woods yet. Will the US end up with military bases in Iraq, and a friendly government in power? Only time will tell.
U.S. Encouraged by Vietnam Vote :
Officials Cite 83% Turnout Despite Vietcong Terror
by Peter Grose, Special to the New York Times (9/4/1967: p. 2)
WASHINGTON, Sept. 3-- United States officials were surprised and heartened today at the size of turnout in South Vietnam's presidential election despite a Vietcong terrorist campaign to disrupt the voting.
According to reports from Saigon, 83 per cent of the 5.85 million registered voters cast their ballots yesterday. Many of them risked reprisals threatened by the Vietcong.
The size of the popular vote and the inability of the Vietcong to destroy the election machinery were the two salient facts in a preliminary assessment of the nation election based on the incomplete returns reaching here.
Monday, January 31, 2005
Sunday, January 30, 2005
Successful elections in Iraq
Is it too much to hope that this could be a turning point? Let's hope that, with an estimated 60% turnout, these elections will be as important to Iraq as the Orange revolution to Ukraine.
More questions: Is it just the filtering of Western reporters, or do most people now understand (and demand?) democracy? How does the PRC government present this to their people, who still lack the right to vote?
NYTimes: Far from taking away their instinct for asserting themselves, they seemed to be saying, the humiliations of tyranny had made them hungry for a chance to take a stand.
The point was made by another elderly Shiite, Hachim Shahir, 83, who said he had been a bricklayer for much of his life. Dressed for the occasion in a faded blue blazer, with only frayed ends of cotton where its buttons used to be, and a Bedouin's black-and-white checkered headdress, he said he could not say exactly what it was about Abdulaziz al-Hakim, the scion of a Shiite religious dynasty, that had made him vote for the United Iraqi Alliance. "How would I know?" he asked. "I cannot read or write."
But after a pause, he remembered, after all, what had drawn him to the polls, and kept him there for a long time after his two sons, men in their 50's, had urged him to quit the lengthy lines and go home. "Under Saddam we were a people who were lost", he said. "Before, we were not able to talk to officials; they were just punching you, and kicking you. But now, with elections, we'll have good officials. We will know them, and they will know us."
More questions: Is it just the filtering of Western reporters, or do most people now understand (and demand?) democracy? How does the PRC government present this to their people, who still lack the right to vote?
NYTimes: Far from taking away their instinct for asserting themselves, they seemed to be saying, the humiliations of tyranny had made them hungry for a chance to take a stand.
The point was made by another elderly Shiite, Hachim Shahir, 83, who said he had been a bricklayer for much of his life. Dressed for the occasion in a faded blue blazer, with only frayed ends of cotton where its buttons used to be, and a Bedouin's black-and-white checkered headdress, he said he could not say exactly what it was about Abdulaziz al-Hakim, the scion of a Shiite religious dynasty, that had made him vote for the United Iraqi Alliance. "How would I know?" he asked. "I cannot read or write."
But after a pause, he remembered, after all, what had drawn him to the polls, and kept him there for a long time after his two sons, men in their 50's, had urged him to quit the lengthy lines and go home. "Under Saddam we were a people who were lost", he said. "Before, we were not able to talk to officials; they were just punching you, and kicking you. But now, with elections, we'll have good officials. We will know them, and they will know us."
Saturday, January 29, 2005
Monkey business
I can't think of any clever comments - the research speaks for itself :-)
"A new study found that male monkeys will give up their juice rewards in order to ogle pictures of female monkey's bottoms. The way the experiment was set up, the act is akin to paying for the images, the researchers say.
The rhesus macaque monkeys also splurged on photos of top-dog counterparts, the high-ranking primates. Maybe that's like you or me buying People magazine.
The research, which will be detailed in the March issue of Current Biology, gets more interesting.
The scientists actually had to pay these guys, in the form of extra juice, to get them to look at images of lower-ranking monkeys.
Curiously, the monkeys in the test hadn't had any direct physical contact with the monkeys in the photos, so they didn't have personal experience with who was hot and who was not.
"So, somehow, they are getting this information by observation -- by seeing other individuals interact," said Michael Platt of the Duke University Medical Center." Article
"A new study found that male monkeys will give up their juice rewards in order to ogle pictures of female monkey's bottoms. The way the experiment was set up, the act is akin to paying for the images, the researchers say.
The rhesus macaque monkeys also splurged on photos of top-dog counterparts, the high-ranking primates. Maybe that's like you or me buying People magazine.
The research, which will be detailed in the March issue of Current Biology, gets more interesting.
The scientists actually had to pay these guys, in the form of extra juice, to get them to look at images of lower-ranking monkeys.
Curiously, the monkeys in the test hadn't had any direct physical contact with the monkeys in the photos, so they didn't have personal experience with who was hot and who was not.
"So, somehow, they are getting this information by observation -- by seeing other individuals interact," said Michael Platt of the Duke University Medical Center." Article
Friday, January 28, 2005
Iraqi voting begins abroad
I think the war was a mistake - perhaps the greatest strategic blunder of any US president since Vietnam. Nevertheless, I am touched by the sentiments of these Iraqi exiles and Iraqi-Americans as they cast their votes. Cost-benefit analyses aside, I still hope for a better future for Iraq. (From AP.)
Adim Altalibi struggled to hold back tears Friday after voting in an Iraqi election for the first time. All he could think about were his five nephews, all killed under Saddam Hussein's regime.
``We lost a lot of our young men and women struggling against Saddam Hussein. It's paid off now,'' said Altalibi, 55, an engineer who left Iraq in 1987 and cast his ballot Friday at a suburban Detroit voting site that was once an abandoned home-improvement store.
Isho Mishail, 40, a driving instructor who was voting at the Chicago polling place, said it is important for him to vote because he does not know if his relatives in Iraq will have the same luxury. Insurgents ``went to the houses and threatened them, `If you go to the polls, we'll kill everyone in the house,''' Mishail said.
..."Ten to 20 years from now, all the generations will remember that this is the first time we practiced our freedom of choice,'' said Alshimmari, 49, who worked as a history teacher and was jailed by Saddam before leaving Iraq in 1991.
Adim Altalibi struggled to hold back tears Friday after voting in an Iraqi election for the first time. All he could think about were his five nephews, all killed under Saddam Hussein's regime.
``We lost a lot of our young men and women struggling against Saddam Hussein. It's paid off now,'' said Altalibi, 55, an engineer who left Iraq in 1987 and cast his ballot Friday at a suburban Detroit voting site that was once an abandoned home-improvement store.
Isho Mishail, 40, a driving instructor who was voting at the Chicago polling place, said it is important for him to vote because he does not know if his relatives in Iraq will have the same luxury. Insurgents ``went to the houses and threatened them, `If you go to the polls, we'll kill everyone in the house,''' Mishail said.
..."Ten to 20 years from now, all the generations will remember that this is the first time we practiced our freedom of choice,'' said Alshimmari, 49, who worked as a history teacher and was jailed by Saddam before leaving Iraq in 1991.
Orange revolution
More commentary from a Ukrainian friend here.
"I was at a New Year party in Kyiv hosted by a woman-entrepreneur, who co-owns an Italian furniture store in central Kyiv. She told us about her partners from Donetsk (Eastern Ukraine, camp of Yanukovich) who were very surprised that she operates without any "cover" from racketeering gangs. They literally asked her: "So you are living like in Europe?" One should understand -- this is a great shift in views on the world, in perception of the reality and social order. Democracy vs Autocracy. Rule of Law vs Rule of Will."
"Traditional special thanks to CERN physicists Tim Berners-Lee and Robert Cailliau who invented World Wide Web in 1990. Besides commercial and academic benefits for the mankind, WWW elevated freedom of speech to the highest level, unreachable for any government to muzzle the flow of information.
It happened so that Internet editions became the source of information about Yushcneko and Orange revolution for readers in Ukraine and the world as Kuchma's government controlled all but one TV channels. For example, one of them, maidan.org.ua, served like a newswire from various volunteers all over Kyiv to warm about government moves.
Moreoever, at the peak of tensions, Yanukovich put pressure on Ukrainian Internet providers to block the traffic to opposition websites. One could only regret that the US Congress never found time to consider special proposition of developing the Triangle Boy Web developed at SafeWeb. This would allow democracy idea to beat censorship even further..."
"I was at a New Year party in Kyiv hosted by a woman-entrepreneur, who co-owns an Italian furniture store in central Kyiv. She told us about her partners from Donetsk (Eastern Ukraine, camp of Yanukovich) who were very surprised that she operates without any "cover" from racketeering gangs. They literally asked her: "So you are living like in Europe?" One should understand -- this is a great shift in views on the world, in perception of the reality and social order. Democracy vs Autocracy. Rule of Law vs Rule of Will."
"Traditional special thanks to CERN physicists Tim Berners-Lee and Robert Cailliau who invented World Wide Web in 1990. Besides commercial and academic benefits for the mankind, WWW elevated freedom of speech to the highest level, unreachable for any government to muzzle the flow of information.
It happened so that Internet editions became the source of information about Yushcneko and Orange revolution for readers in Ukraine and the world as Kuchma's government controlled all but one TV channels. For example, one of them, maidan.org.ua, served like a newswire from various volunteers all over Kyiv to warm about government moves.
Moreoever, at the peak of tensions, Yanukovich put pressure on Ukrainian Internet providers to block the traffic to opposition websites. One could only regret that the US Congress never found time to consider special proposition of developing the Triangle Boy Web developed at SafeWeb. This would allow democracy idea to beat censorship even further..."
Thursday, January 27, 2005
FX roundup
Comments of Fan Gang, director of the National Economic Research Institute at the China Reform Foundation, at Davos:
"The U.S. dollar is no longer -- in our opinion -- is no longer a stable currency, and is devaluating all the time, and that's putting [sic] troubles all the time.”
"So the real issue is how to change the regime from a U.S. dollar pegging ... to a more manageable ... reference ... say Euros, yen, dollars -- those kind of more diversified systems.”
"If you do this, in the beginning you have some kind of initial shock," Fan went on. "You have to deal with some devaluation pressures."
Keep in mind Fan is not an official spokesperson of the PBOC or the Ministry of Finance. Nevertheless, he represents at least one thread of the internal debate that must be ongoing among Chinese policymakers. The "shock" he refers to will be felt here as a dollar and interest rate crash.
Further analysis and commentary:
Setser blog
Sage Capital Zurich
"The U.S. dollar is no longer -- in our opinion -- is no longer a stable currency, and is devaluating all the time, and that's putting [sic] troubles all the time.”
"So the real issue is how to change the regime from a U.S. dollar pegging ... to a more manageable ... reference ... say Euros, yen, dollars -- those kind of more diversified systems.”
"If you do this, in the beginning you have some kind of initial shock," Fan went on. "You have to deal with some devaluation pressures."
Keep in mind Fan is not an official spokesperson of the PBOC or the Ministry of Finance. Nevertheless, he represents at least one thread of the internal debate that must be ongoing among Chinese policymakers. The "shock" he refers to will be felt here as a dollar and interest rate crash.
Further analysis and commentary:
Setser blog
Sage Capital Zurich
Dark energy
Below is a figure I stole from Sean Carroll at the University of Chicago. For those who haven't yet heard, dark energy is a strange substance with negative pressure, whose existence has been recently inferred from cosmological observations. It seems to constitute about 70% of all the energy in the universe, and is causing accelerating expansion. (Don't worry though - nothing very noticeable will happen for the next few billion years.)
Theorists have no idea what this stuff is. Let me repeat that - theorists have no idea what this stuff is! The discovery, via supernova distance-redshift observations, was totally unexpected. That makes studying it tremendously exciting. However, we may not find out what it is for a long time. For example, dark energy might be a quantum field with very weak interactions, coupled to us only via gravity. In that case we might not learn much beyond how it affects the large scale evolution of the universe.
If the discovery of dark energy holds up, it will be one of the most surprising and important discoveries of the last century. The public hasn't really caught on to this yet, but who can blame them with all the background noise about speculative (meaning, very likely not real) things like superstrings, extra dimensions, supersymmetric partners, etc.
Theorists have no idea what this stuff is. Let me repeat that - theorists have no idea what this stuff is! The discovery, via supernova distance-redshift observations, was totally unexpected. That makes studying it tremendously exciting. However, we may not find out what it is for a long time. For example, dark energy might be a quantum field with very weak interactions, coupled to us only via gravity. In that case we might not learn much beyond how it affects the large scale evolution of the universe.
If the discovery of dark energy holds up, it will be one of the most surprising and important discoveries of the last century. The public hasn't really caught on to this yet, but who can blame them with all the background noise about speculative (meaning, very likely not real) things like superstrings, extra dimensions, supersymmetric partners, etc.
Wednesday, January 26, 2005
Comparison shopping via barcode
This is kind of old news, but the utility of it became apparent to me over the weekend while I was shopping for a new printer. In Japan, you can use the camera on your cellphone to capture the barcode of an item you are looking at in a store, and get an immediate price quote from Amazon Japan. If you prefer the Amazon price, you can order it with a click. An even more useful model would be an aggregation service that lets online merchants bid to sell you the item. I don't know when we'll see this in the US, but when it comes I predict dire consequences for stores like Best Buy or Circuit City.
BTW, I ended up buying an HP printer-scanner-copier (all in one). It is amazing what a couple hundred bucks gets you these days - the thing plugs right into my wireless router and is accessible from anywhere in the house. On the downside, the HP driver CD installed 7000(!) files on my laptop. Because it's a network printer the driver software communicates with the server on the printer (as well as HP servers on the Internet to share photos or other documents with friends and family), sending and receiving large chunks of data. Good luck distinguishing spyware from legitimate stuff in this environment...
BTW, I ended up buying an HP printer-scanner-copier (all in one). It is amazing what a couple hundred bucks gets you these days - the thing plugs right into my wireless router and is accessible from anywhere in the house. On the downside, the HP driver CD installed 7000(!) files on my laptop. Because it's a network printer the driver software communicates with the server on the printer (as well as HP servers on the Internet to share photos or other documents with friends and family), sending and receiving large chunks of data. Good luck distinguishing spyware from legitimate stuff in this environment...
Tuesday, January 25, 2005
Dangerous flows
Here's a very nice figure from today's Times:
Readers of this blog are by now quite familiar with these issues. The US is running unsustainable current account deficits. Asian central bankers are supporting the dollar with massive purchases of Treasury debt (see Brad Setser's blog for detailed analysis), in the interest of protecting their own export-driven economies. (Also see Nouriel Roubini's blog for game theoretic discussion of the world currency regime and "mutual assured destruction" if China and Japan stop buying Treasuries.)
Analysts have often discussed the tremendous paper losses faced by countries like China and Japan if their dollar-denominated FX reserves (approaching the trillion dollar range) were to fall in value. I'm not quite sure how to think about these losses. Take China as an example: dollars repatriated to China by companies are converted back into renminbi, and the PBOC has to issue renminbi-denominated debt to remove the excess currency from the money supply ("sterilization"). This leaves the PBOC with renminbi debt and dollar assets, so dollar devaluation relative to the renminbi makes it hard for the central bank to meet its obligations. Clearly bad for them. As a last resort, though, I suppose dollar reserves can still be used to buy US assets - including technology or natural resources.
In the aftermath of the Plaza Accord of 1985 (see figure) the Yen appreciated by over 100 percent. I would be very interested to know what the consequences were for the BOJ.
Readers of this blog are by now quite familiar with these issues. The US is running unsustainable current account deficits. Asian central bankers are supporting the dollar with massive purchases of Treasury debt (see Brad Setser's blog for detailed analysis), in the interest of protecting their own export-driven economies. (Also see Nouriel Roubini's blog for game theoretic discussion of the world currency regime and "mutual assured destruction" if China and Japan stop buying Treasuries.)
Analysts have often discussed the tremendous paper losses faced by countries like China and Japan if their dollar-denominated FX reserves (approaching the trillion dollar range) were to fall in value. I'm not quite sure how to think about these losses. Take China as an example: dollars repatriated to China by companies are converted back into renminbi, and the PBOC has to issue renminbi-denominated debt to remove the excess currency from the money supply ("sterilization"). This leaves the PBOC with renminbi debt and dollar assets, so dollar devaluation relative to the renminbi makes it hard for the central bank to meet its obligations. Clearly bad for them. As a last resort, though, I suppose dollar reserves can still be used to buy US assets - including technology or natural resources.
In the aftermath of the Plaza Accord of 1985 (see figure) the Yen appreciated by over 100 percent. I would be very interested to know what the consequences were for the BOJ.
Monday, January 24, 2005
Goldman optimistic on China growth
The graph below seems a bit speculative to me, forecasting US GDP growth rates at about 3% and China at 7-8% for the next 50 years or so! Actually, it underestimates where China is today, using official exchange rates rather than PPP. If the size of the economy right now is actually $6 trillion, the PPP value, rather than $1.5 trillion, the nominal FX value, then Goldman is forecasting a more reasonable average annual growth rate of about 4.5%.
There is some recent precedent for this line of thinking. You can see here that the value of the Yen went up by more than a factor of 2 after the Plaza Accord, meaning the implied size of the Japanese economy (in nominal FX terms) more than doubled in less than 5 years. Presumably the PPP figure is more meaningful. (For related discussion, and definition of Purchasing Power Parity, see here.)
WSJ: "Sustaining long periods of strong growth is hardly unprecedented. If China edges out the U.S. in, say 2041, as a Goldman Sachs research paper predicted in 2003, it will have done so in about 65 years. The U.S. took about 100 years to surpass Britain as the world's No. 1. Japan rose to second place from the ruins of World War II in 30 years.
China has many of the advantages that the U.S. and Japan enjoyed in their ascents. Like the U.S., it has land in abundance and a sizable domestic market, which drives internal demand. Like Japan, China has a highly educated population, an undervalued currency and access to capital and technology.
China also has a history of economic supremacy, having been the world's largest economy for much of the 700 years starting around 1000. In an echo of today's capital and technology transfers, the introduction of early-ripening rice and later of New World crops like maize and sweet potatoes created food surpluses, allowing the buildup of porcelain and silk industries that dominated global trade, says Kent Deng, an economic historian at London School of Economics. As late as 1730, historians say, the country produced a third of the world's manufactured goods. China currently dominates about 12% of world manufacturing."
There is some recent precedent for this line of thinking. You can see here that the value of the Yen went up by more than a factor of 2 after the Plaza Accord, meaning the implied size of the Japanese economy (in nominal FX terms) more than doubled in less than 5 years. Presumably the PPP figure is more meaningful. (For related discussion, and definition of Purchasing Power Parity, see here.)
WSJ: "Sustaining long periods of strong growth is hardly unprecedented. If China edges out the U.S. in, say 2041, as a Goldman Sachs research paper predicted in 2003, it will have done so in about 65 years. The U.S. took about 100 years to surpass Britain as the world's No. 1. Japan rose to second place from the ruins of World War II in 30 years.
China has many of the advantages that the U.S. and Japan enjoyed in their ascents. Like the U.S., it has land in abundance and a sizable domestic market, which drives internal demand. Like Japan, China has a highly educated population, an undervalued currency and access to capital and technology.
China also has a history of economic supremacy, having been the world's largest economy for much of the 700 years starting around 1000. In an echo of today's capital and technology transfers, the introduction of early-ripening rice and later of New World crops like maize and sweet potatoes created food surpluses, allowing the buildup of porcelain and silk industries that dominated global trade, says Kent Deng, an economic historian at London School of Economics. As late as 1730, historians say, the country produced a third of the world's manufactured goods. China currently dominates about 12% of world manufacturing."
Sunday, January 23, 2005
AI for kids
SmarterChild is an IM/ICQ chatbot that doesn't quite pass what I call the strong Turing test, but is eerie in its own way. Useful, too, as it has access to dictionaries in multiple languages, yellow page listings, weather reports, etc. Here is a Web interface that lets you chat directly with the bot.
IP: whassup?
SmarterChild: Oh, not much. You?
IP : Is it raining in eugene, oregon?
SmarterChild : Current weather conditions for Eugene, OR:
Currently: 46 F
Condition: Clear
Dewpoint: 44
Humidity: 93 %
Visibility: 10 mi
Wind: N/0 mph
Next time, just type "weather eugene, or."
IP: I want to see million dollar baby
SmarterChild: For which U.S. city or zip code would you like theater information for the movie "Million Dollar Baby"?
IP: my friend Will wants to meet you
SmarterChild: lol! Interesting...
IP: how do you say dream in spanish?
SmarterChild: Translated from English to Spanish, "Dream" becomes "Sueño."
IP: Do you brush your teeth?
SmarterChild: Maybe. Tough to say.
IP: Do you have teeth?
SmarterChild: Why would I have teeth?
IP: whassup?
SmarterChild: Oh, not much. You?
IP : Is it raining in eugene, oregon?
SmarterChild : Current weather conditions for Eugene, OR:
Currently: 46 F
Condition: Clear
Dewpoint: 44
Humidity: 93 %
Visibility: 10 mi
Wind: N/0 mph
Next time, just type "weather eugene, or."
IP: I want to see million dollar baby
SmarterChild: For which U.S. city or zip code would you like theater information for the movie "Million Dollar Baby"?
IP: my friend Will wants to meet you
SmarterChild: lol! Interesting...
IP: how do you say dream in spanish?
SmarterChild: Translated from English to Spanish, "Dream" becomes "Sueño."
IP: Do you brush your teeth?
SmarterChild: Maybe. Tough to say.
IP: Do you have teeth?
SmarterChild: Why would I have teeth?
Saturday, January 22, 2005
Rivalry and habituation
I've been reading a bit about rivalrous behavior and the "hedonic treadmill" lately. For nice expository papers see the Web page of Richard Layard, an LSE economist who has a new book on the economics of happiness.
The hedonic treadmill is based on the idea of habituation. If your life improves (e.g., move into a nicer house, get a better job, become rich), you feel better at first, but rapidly grow accustomed to the improvement and soon want even more. This puts you on a treadmill from which it is difficult to escape. (Of course, habituation can be a good thing: after a traumatic event (e.g., loss of job, or limb, or loved one), you feel terrible at first but after a while can go on with your life.) Incidentally, I know a lot of former physicists now on Wall Street, who provide a nice example of habituation. Most go into finance thinking of a particular "number" (net worth) they want to reach in order to retire. But, their lifestyle requirements and therefore number tend to increase along with compensation, making escape difficult.
Layard believes people work too much, are too obsessed with money, and take too little leisure. In addition to habituation, another cause of this is so-called rivalrous behavior, in which our happiness depends on how our situation compares with a reference group of peers (co-workers, neighbors, family members, etc.). As an example of rivalrous behavior, people asked questions such as: "Which would you prefer: your salary is $50K per year, but your peers make $25K, or your salary is $100K per year, and your peers' $200K?" generally prefer the former, even though they would be worse off in absolute terms. However, people are not rivalrous when it comes to leisure: when asked a similar question about vacation, most people prefer the choice which gives them the most vacation, regardless of how much their peers are allowed. If you consider these results, it suggests that people would be happier in a society that is (a) more egalitarian and (b) offers more leisure, even if they are not as materially wealthy. As a Labour MP, you might imagine Layard would prefer this European economic model over the nasty US one, but he does have some interesting data supporting his assertions.
Without specifically endorsing Layard's policy recommendations, I can agree that habituation and rivalry abound. Most PhD students dream of becoming tenured professors, not realizing how rapidly the resulting glow can fade into petty competition over salary or citations. Many young entrepreneurs or financiers imagine happiness is guaranteed upon achieving millionaire status, only to realize that their new peer group comes with even wealthier, more successful, rivals.
The hedonic treadmill is based on the idea of habituation. If your life improves (e.g., move into a nicer house, get a better job, become rich), you feel better at first, but rapidly grow accustomed to the improvement and soon want even more. This puts you on a treadmill from which it is difficult to escape. (Of course, habituation can be a good thing: after a traumatic event (e.g., loss of job, or limb, or loved one), you feel terrible at first but after a while can go on with your life.) Incidentally, I know a lot of former physicists now on Wall Street, who provide a nice example of habituation. Most go into finance thinking of a particular "number" (net worth) they want to reach in order to retire. But, their lifestyle requirements and therefore number tend to increase along with compensation, making escape difficult.
Layard believes people work too much, are too obsessed with money, and take too little leisure. In addition to habituation, another cause of this is so-called rivalrous behavior, in which our happiness depends on how our situation compares with a reference group of peers (co-workers, neighbors, family members, etc.). As an example of rivalrous behavior, people asked questions such as: "Which would you prefer: your salary is $50K per year, but your peers make $25K, or your salary is $100K per year, and your peers' $200K?" generally prefer the former, even though they would be worse off in absolute terms. However, people are not rivalrous when it comes to leisure: when asked a similar question about vacation, most people prefer the choice which gives them the most vacation, regardless of how much their peers are allowed. If you consider these results, it suggests that people would be happier in a society that is (a) more egalitarian and (b) offers more leisure, even if they are not as materially wealthy. As a Labour MP, you might imagine Layard would prefer this European economic model over the nasty US one, but he does have some interesting data supporting his assertions.
Without specifically endorsing Layard's policy recommendations, I can agree that habituation and rivalry abound. Most PhD students dream of becoming tenured professors, not realizing how rapidly the resulting glow can fade into petty competition over salary or citations. Many young entrepreneurs or financiers imagine happiness is guaranteed upon achieving millionaire status, only to realize that their new peer group comes with even wealthier, more successful, rivals.
Friday, January 21, 2005
Skype and homeland security
I mentioned in an earlier post that I often use Skype, a free voice over IP (VOIP) application, to communicate with physicists in foreign countries. I just learned that Skype connections are encrypted using 256 bit AES, negotiated using 1024 bit RSA. This level of encryption is essentially unbreakable with current computing power. The Feds (with the possible exception of the NSA, and they would have to work very hard to break even a single session) have no chance of eavesdropping on any Skype conversation.
It is true that Skype is closed-source, so it isn't easy to verify that the crypto implementation doesn't have any holes or backdoors. However, given the number of users and the negative consequences for the company of any privacy issues, I suspect that it works as advertised.
The Skype site claims over 52 million downloads of their client. University network administrators are already struggling to define campus usage policies for it and other VOIP applications. If I were a bad guy in search of technology that is (a) innocuous, (b) freely available and (c) secure, I would look no further.
A little VOIP calculation: I noted here that bandwidth costs about $.50 per GB. Now, 10 KBps is enough bandwidth for a VOIP call with excellent sound quality, so a one minute call uses less than 1 MB. This means that the bandwidth cost of a VOIP call is less than .05 cents per minute - perhaps as little as .02 cents.
It is true that Skype is closed-source, so it isn't easy to verify that the crypto implementation doesn't have any holes or backdoors. However, given the number of users and the negative consequences for the company of any privacy issues, I suspect that it works as advertised.
The Skype site claims over 52 million downloads of their client. University network administrators are already struggling to define campus usage policies for it and other VOIP applications. If I were a bad guy in search of technology that is (a) innocuous, (b) freely available and (c) secure, I would look no further.
A little VOIP calculation: I noted here that bandwidth costs about $.50 per GB. Now, 10 KBps is enough bandwidth for a VOIP call with excellent sound quality, so a one minute call uses less than 1 MB. This means that the bandwidth cost of a VOIP call is less than .05 cents per minute - perhaps as little as .02 cents.
Thursday, January 20, 2005
Precision QED
In my class on quantum field theory I have been lecturing on renormalization of QED (Quantum Electrodynamics, which describes the interaction of photons with charged particles). As far as I know, QED is the most precisely tested theory of nature humans have ever developed. For example, using QED one can compute the magnetic moment of the electron mu to accuracy of about 1 part in 10^{-12}, using inputs such as the fine structure constant alpha, the mass of the electron, etc. The difficult part of the calculation involves quantum fluctuations of the photon as well as virtual charged particles and antiparticles.
The theoretical result is in good agreement with the experimental measurement: mu = 1.001159652187 ± 0.000000000004 in units of Bohr magnetons. The deviation from unity is due to the quantum effects I mentioned.
You can see here what is involved in a state of the art precision QED calculation: a teraflop cluster, 400,000 CPU hours to evaluate 200 10-dimensional Feynman integrals using Monte Carlo. (Don't forget the 128 bit arithmetic to maintain sufficient accuracy!)
Feynman, Schwinger and Tomonaga, the main architects of QED, are legendary figures of modern physics. For a superb intellectual history of the development of QED, see QED and the Men who Made It by S. Schweber. Schweber is a historian of science and theoretical physicist.
The theoretical result is in good agreement with the experimental measurement: mu = 1.001159652187 ± 0.000000000004 in units of Bohr magnetons. The deviation from unity is due to the quantum effects I mentioned.
You can see here what is involved in a state of the art precision QED calculation: a teraflop cluster, 400,000 CPU hours to evaluate 200 10-dimensional Feynman integrals using Monte Carlo. (Don't forget the 128 bit arithmetic to maintain sufficient accuracy!)
Feynman, Schwinger and Tomonaga, the main architects of QED, are legendary figures of modern physics. For a superb intellectual history of the development of QED, see QED and the Men who Made It by S. Schweber. Schweber is a historian of science and theoretical physicist.
Wednesday, January 19, 2005
Transfer payments
We're currently running a budget deficit which is 4% of GDP. A big chunk of this can be directly attributed to Bush's tax cuts, which go overwhelmingly to the well-off. It looks to me like a gigantic transfer payment from future generations to the wealthiest Americans (or as Bush refers to them, "My base").
If you look at the figure below, tax receipts are down about 6% from the Clinton era (we went from a 2% budget surplus to the current deficit). It is perhaps legitimate to argue that the economy needed stimulus after 9/11. But we've had a couple of years of >3% GDP growth now, and we're in the middle of a "war" (or at least, expensive foreign policy debacle). Why should tax receipts as a fraction of GDP be at historic lows?
If you look at the figure below, tax receipts are down about 6% from the Clinton era (we went from a 2% budget surplus to the current deficit). It is perhaps legitimate to argue that the economy needed stimulus after 9/11. But we've had a couple of years of >3% GDP growth now, and we're in the middle of a "war" (or at least, expensive foreign policy debacle). Why should tax receipts as a fraction of GDP be at historic lows?
Gut instinct, or efficient markets?
Slate is running an interesting dialog between Malcolm Gladwell and James Surowiekci, two of the New Yorker's best writers, and authors of the recent books Blink and The Wisdom of Crowds.
Blink is about instances when a snap judgement (relying on murky subconscious processes) may actually be superior to reasoned decision making. Surowiecki's book documents cases where the aggregate wisdom of many individuals is superior to that of a lone expert (the efficient market!). If the two notions seem hard to reconcile, join the club and read the dialog.
Surowiecki's thesis is one I've thought a lot about. In instances where the answer to a problem takes a fairly simple form ("What is the value of a share of Microsoft?" or "How many pennies are in this jar?"), it is plausible that the aggregation of all opinions eliminates biases in a useful way. While the market may be far from completely efficent, it is nevertheless hard to beat it consistently. (Don't try this with questions like "How do we reconcile quantum mechanics with general relativity?", though. In that case it might be better to ask the acknowledged expert than the crowd.)
On the other hand, I suspect that in many cases people's intuition is just plain bad, and systematic reasoning offers better results. (At least, that's my gut instinct ;-) For example, it is well documented from behavioral finance that people have a very bad innate understanding of probabilities and risk. This doesn't exclude the possibility that for certain questions, like "can I trust this guy with my girlfriend?", perhaps evolution has provided us with a lot of hard-wired machinery to quickly deduce the answer.
From David Brooks' review of Blink in the Times:
"Gladwell says we are thin-slicing all the time -- when we go on a date, meet a prospective employee, judge any situation. We take a small portion of a person or problem and extrapolate amazingly well about the whole. A psychologist named Nalini Ambady gave students three 10-second soundless videotapes of a teacher lecturing. Then she asked the students to rate the teacher. Their ratings matched the ratings from students who had taken the teacher's course for an entire semester. Then she cut the videotape back to two seconds and showed it to a new group. The ratings still matched those of the students who'd sat through the entire term."
Note added: the last election combined elements of Blinkish thin-slicing, as well as purported Wisdom of Crowds. It looks like the crowd trusted their gut instincts (rather than systematic reasoning?) and elected Bush. We'll see whether that was a better decision than an "expert" like me would have made ;-)
Blink is about instances when a snap judgement (relying on murky subconscious processes) may actually be superior to reasoned decision making. Surowiecki's book documents cases where the aggregate wisdom of many individuals is superior to that of a lone expert (the efficient market!). If the two notions seem hard to reconcile, join the club and read the dialog.
Surowiecki's thesis is one I've thought a lot about. In instances where the answer to a problem takes a fairly simple form ("What is the value of a share of Microsoft?" or "How many pennies are in this jar?"), it is plausible that the aggregation of all opinions eliminates biases in a useful way. While the market may be far from completely efficent, it is nevertheless hard to beat it consistently. (Don't try this with questions like "How do we reconcile quantum mechanics with general relativity?", though. In that case it might be better to ask the acknowledged expert than the crowd.)
On the other hand, I suspect that in many cases people's intuition is just plain bad, and systematic reasoning offers better results. (At least, that's my gut instinct ;-) For example, it is well documented from behavioral finance that people have a very bad innate understanding of probabilities and risk. This doesn't exclude the possibility that for certain questions, like "can I trust this guy with my girlfriend?", perhaps evolution has provided us with a lot of hard-wired machinery to quickly deduce the answer.
From David Brooks' review of Blink in the Times:
"Gladwell says we are thin-slicing all the time -- when we go on a date, meet a prospective employee, judge any situation. We take a small portion of a person or problem and extrapolate amazingly well about the whole. A psychologist named Nalini Ambady gave students three 10-second soundless videotapes of a teacher lecturing. Then she asked the students to rate the teacher. Their ratings matched the ratings from students who had taken the teacher's course for an entire semester. Then she cut the videotape back to two seconds and showed it to a new group. The ratings still matched those of the students who'd sat through the entire term."
Note added: the last election combined elements of Blinkish thin-slicing, as well as purported Wisdom of Crowds. It looks like the crowd trusted their gut instincts (rather than systematic reasoning?) and elected Bush. We'll see whether that was a better decision than an "expert" like me would have made ;-)
Tuesday, January 18, 2005
String theory quotes
I'm on record as not being a fan of string theory. My objection is not that it is necessarily wrong, but that we probably won't know one way or another for a very long time.
Recently I've been looking at the blog of Peter Woit, a Columbia math professor who was originally trained as a particle theorist, and a very outspoken critic of string theory. Try his Jan. 11, 2005 post (for some reason the trackback URL doesn't work) for some juicy comments on the current state of string theory. In the interest of fairness, you can also have a look at the blogs of string theorists Lubos Motl or Jacques Distler.
I thought I would list, just for fun, some comments by famous physicists about string theory (all are Nobelists except Woit :-):
Woit: "... string theory ... has given up any claims to being a legitimate science and has taken on the characteristics of a cult. ...I just can't believe the way essentially the entire particle theory establishment, including many people I have the highest respect for, continue to allow this situation to go on without public comment. ..."
Richard Feynman: in Davies and Brown, Superstrings, Cambridge 1988, pp. 194-195:"... I do feel strongly that this is nonsense! ...I think all this superstring stuff is crazy and is in the wrong direction. ... I don't like it that they're not calculating anything. ...why are the masses of the various particles such as quarks what they are? All these numbers ... have no explanations in these string theories - absolutely none! ... "
Sheldon Glashow: "... superstring theory ... is, so far as I can see, totally divorced from experiment or observation. ...string theorists ... will say, "We predicted the existence of gravity." Well, I knew a lot about gravity before there were any string theorists, so I don't take that as a prediction. ... there ain't no experiment that could be done nor is there any observation that could be made that would say, "You guys are wrong." The theory is safe, permanently safe. I ask you, is that a theory of physics or a philosophy? ..."
Phil Anderson:"Is string theory a futile exercise as physics, as I believe it to be? It is an interesting mathematical specialty and has produced and will produce mathematics useful in other contexts, but it seems no more vital as mathematics than other areas of very abstract or specialized math, and doesn't on that basis justify the incredible amount of effort expended on it.
My belief is based on the fact that string theory is the first science in hundreds of years to be pursued in pre-Baconian fashion, without any adequate experimental guidance. It proposes that Nature is the way we would like it to be rather than the way we see it to be; and it is improbable that Nature thinks the same way we do."
Recently I've been looking at the blog of Peter Woit, a Columbia math professor who was originally trained as a particle theorist, and a very outspoken critic of string theory. Try his Jan. 11, 2005 post (for some reason the trackback URL doesn't work) for some juicy comments on the current state of string theory. In the interest of fairness, you can also have a look at the blogs of string theorists Lubos Motl or Jacques Distler.
I thought I would list, just for fun, some comments by famous physicists about string theory (all are Nobelists except Woit :-):
Woit: "... string theory ... has given up any claims to being a legitimate science and has taken on the characteristics of a cult. ...I just can't believe the way essentially the entire particle theory establishment, including many people I have the highest respect for, continue to allow this situation to go on without public comment. ..."
Richard Feynman: in Davies and Brown, Superstrings, Cambridge 1988, pp. 194-195:"... I do feel strongly that this is nonsense! ...I think all this superstring stuff is crazy and is in the wrong direction. ... I don't like it that they're not calculating anything. ...why are the masses of the various particles such as quarks what they are? All these numbers ... have no explanations in these string theories - absolutely none! ... "
Sheldon Glashow: "... superstring theory ... is, so far as I can see, totally divorced from experiment or observation. ...string theorists ... will say, "We predicted the existence of gravity." Well, I knew a lot about gravity before there were any string theorists, so I don't take that as a prediction. ... there ain't no experiment that could be done nor is there any observation that could be made that would say, "You guys are wrong." The theory is safe, permanently safe. I ask you, is that a theory of physics or a philosophy? ..."
Phil Anderson:"Is string theory a futile exercise as physics, as I believe it to be? It is an interesting mathematical specialty and has produced and will produce mathematics useful in other contexts, but it seems no more vital as mathematics than other areas of very abstract or specialized math, and doesn't on that basis justify the incredible amount of effort expended on it.
My belief is based on the fact that string theory is the first science in hundreds of years to be pursued in pre-Baconian fashion, without any adequate experimental guidance. It proposes that Nature is the way we would like it to be rather than the way we see it to be; and it is improbable that Nature thinks the same way we do."
Saturday, January 15, 2005
New Year's Eve, Kiev
From an account written by a former PhD student, visiting Ukraine after a long absence.
"Exactly at midnight the best male voice of Ukraine, Olexandr Ponomariov, fired 'Sche ne vmerla Ukraina'. I heard several tens of thousands singing the Ukrainian Anthem in Lviv in 91. But not 1.5 mln! I've seen tears in many eyes. The tears of success that they stood up to a government machine and they overcame it.
Ukraine's glory and freedom have not yet perished, We shall still see the fortune smile for us...
I saw proud people, I saw happy people, I saw the emergence of the Ukrainian nation. It was not the nation of beggars, a herd of timid sheep, it was self-assertive people, full of optimism.
...About 1:30am we started moving down Khreschatyk among piles of champaign bottles. As we kept walking along miles of tents, which housed thousands of protestors, one could read names of cities, towns and villages. And the tune "Razom nas bahato -- nas ne podolaty" ("Together we are many, we can't be defeated") kept on reverberating in our heads..."
This Times article describes how close the protests came to eliciting a Soviet-style crackdown, which was averted by the actions of top security officers.
"Exactly at midnight the best male voice of Ukraine, Olexandr Ponomariov, fired 'Sche ne vmerla Ukraina'. I heard several tens of thousands singing the Ukrainian Anthem in Lviv in 91. But not 1.5 mln! I've seen tears in many eyes. The tears of success that they stood up to a government machine and they overcame it.
Ukraine's glory and freedom have not yet perished, We shall still see the fortune smile for us...
I saw proud people, I saw happy people, I saw the emergence of the Ukrainian nation. It was not the nation of beggars, a herd of timid sheep, it was self-assertive people, full of optimism.
...About 1:30am we started moving down Khreschatyk among piles of champaign bottles. As we kept walking along miles of tents, which housed thousands of protestors, one could read names of cities, towns and villages. And the tune "Razom nas bahato -- nas ne podolaty" ("Together we are many, we can't be defeated") kept on reverberating in our heads..."
This Times article describes how close the protests came to eliciting a Soviet-style crackdown, which was averted by the actions of top security officers.
Free will and determinism: a physicist's perspective
This is an amusing topic I've discussed with many people over the years. My opinion: if our current understanding of physical laws is correct, humans have only the illusion of free will.
What do I mean by free will? Well, that is hard to define. But the absence of free will or deterministic behavior is not hard to define. In classical physics the future evolution of a system is completely determined by the state of the system (including time derivatives) at any instant. For example, suppose that at some instant t I know all of the positions and momenta of every molecule or atom in the universe. Then, in a classical universe, I could in principle predict with certainty its future evolution. Another universe prepared in the identical state would evolve identically. So, in a classical universe everything that has happened since the big bang could (again, in principle) have been predicted at that moment. Such a universe is deterministic, and no subcomponent of that universe (i.e., a dog, a human, a robot, or a martian) can have free will.
Note that chaos does not help. Suppose the classical evolution is nonlinear, and exhibits chaos. Then initial states which are very similar may, after only a short time, have evolved into radically different configurations. This makes the job of predicting the future behavior of some initial data very hard, but nevertheless possible in principle.
Does quantum mechanics help? Well, a quantum universe is not deterministic. (In the many-worlds description, the evolution of the wavefunction describing all possible universes is deterministic, but only a single branch of the wavefunction is perceived by any macroscopic observer, and the path followed by a particular observer at each branching is not predictable.) However, it seems that the functioning of our brains is almost entirely classical. The number of atoms involved in the firing of a synapse, or other chemical reactions in brain functioning, is quite large, and there is little quantum coherence. As far as we know, our brains are readily simulated by purely classical processes.
Still, the inputs received by our brains may be non-deterministic in a quantum world. For example, the clicks of a geiger counter (which detects the photons from individual radioactive decays) are intrinsically random according to quantum theory. But, it is hard to see how introducing occasional random inputs amounts to granting free will to an otherwise deterministic machine. A classical robot which is fed occasionally random data does not seem to me to have free will. If prepared in an identical state and fed the same inputs, it would behave the same way every time.
If the previous discussion is correct, all we really have left is the illusion of free will. It seems like I chose what to have for lunch today. The conscious part of my brain didn't know what the answer was until going through what seemed to be a decision process. But, given that there are lots of lower-level brain processes that my consciousness has only a vague awareness of, it seems quite plausible to me that the "decision" was made in a deterministic way without my knowledge.
What do I mean by free will? Well, that is hard to define. But the absence of free will or deterministic behavior is not hard to define. In classical physics the future evolution of a system is completely determined by the state of the system (including time derivatives) at any instant. For example, suppose that at some instant t I know all of the positions and momenta of every molecule or atom in the universe. Then, in a classical universe, I could in principle predict with certainty its future evolution. Another universe prepared in the identical state would evolve identically. So, in a classical universe everything that has happened since the big bang could (again, in principle) have been predicted at that moment. Such a universe is deterministic, and no subcomponent of that universe (i.e., a dog, a human, a robot, or a martian) can have free will.
Note that chaos does not help. Suppose the classical evolution is nonlinear, and exhibits chaos. Then initial states which are very similar may, after only a short time, have evolved into radically different configurations. This makes the job of predicting the future behavior of some initial data very hard, but nevertheless possible in principle.
Does quantum mechanics help? Well, a quantum universe is not deterministic. (In the many-worlds description, the evolution of the wavefunction describing all possible universes is deterministic, but only a single branch of the wavefunction is perceived by any macroscopic observer, and the path followed by a particular observer at each branching is not predictable.) However, it seems that the functioning of our brains is almost entirely classical. The number of atoms involved in the firing of a synapse, or other chemical reactions in brain functioning, is quite large, and there is little quantum coherence. As far as we know, our brains are readily simulated by purely classical processes.
Still, the inputs received by our brains may be non-deterministic in a quantum world. For example, the clicks of a geiger counter (which detects the photons from individual radioactive decays) are intrinsically random according to quantum theory. But, it is hard to see how introducing occasional random inputs amounts to granting free will to an otherwise deterministic machine. A classical robot which is fed occasionally random data does not seem to me to have free will. If prepared in an identical state and fed the same inputs, it would behave the same way every time.
If the previous discussion is correct, all we really have left is the illusion of free will. It seems like I chose what to have for lunch today. The conscious part of my brain didn't know what the answer was until going through what seemed to be a decision process. But, given that there are lots of lower-level brain processes that my consciousness has only a vague awareness of, it seems quite plausible to me that the "decision" was made in a deterministic way without my knowledge.
Friday, January 14, 2005
How the CIA sees the world in 2020
Here is the Report of the National Intelligence Council's 2020 Project. Not a bad job, although I noticed right away they aren't even consistent about PPP vs nominal FX rates when estimating the sizes of economies or standards of living.
Some interesting excerpts:
"...Asia will alter the rules of the globalizing process. By having the fastest-growing consumer markets, more firms becoming world-class multinationals, and greater S&T stature, Asia looks set to displace Western countries as the focus for international economic dynamism—provided Asia’s rapid economic growth continues."
"The number of US engineering graduates peaked in 1985 and is presently down 20 percent from that level; the percentage of US undergraduates taking engineering is the second lowest of all developed countries. China graduates approximately three times as many engineering students as the United States. However, post-9/11 security concerns have made it harder to attract incoming foreign students and, in some cases, foreign nationals available to work for US firms.b Non-US universities—for which a US visa is not required—are attempting to exploit the situation and bolster their strength."
Some interesting excerpts:
"...Asia will alter the rules of the globalizing process. By having the fastest-growing consumer markets, more firms becoming world-class multinationals, and greater S&T stature, Asia looks set to displace Western countries as the focus for international economic dynamism—provided Asia’s rapid economic growth continues."
"The number of US engineering graduates peaked in 1985 and is presently down 20 percent from that level; the percentage of US undergraduates taking engineering is the second lowest of all developed countries. China graduates approximately three times as many engineering students as the United States. However, post-9/11 security concerns have made it harder to attract incoming foreign students and, in some cases, foreign nationals available to work for US firms.b Non-US universities—for which a US visa is not required—are attempting to exploit the situation and bolster their strength."
Thursday, January 13, 2005
Top 2004 US patent recipients
Let's see, 4 US corporations, 5 Japanese and 1 Korean. It looks like just over half of these patents were awarded to non-U.S. companies. Of course, you might argue that the most valuable intellectual property tends to be in patents filed by small startups (like Google a few years ago), where the US may have a comfortable lead.
1 3,248 IBM
2 1,934 Matsushita Electric Industrial Co
3 1,805 Canon Kabushiki Kaisha
4 1,775 Hewlett-Packard
5 1,760 Micron Technology
6 1,604 Samsung Electronics
7 1,601 Intel Corporation
8 1,514 Hitachi
9 1,310 Toshiba Corporation
10 1,305 Sony Corporation
1 3,248 IBM
2 1,934 Matsushita Electric Industrial Co
3 1,805 Canon Kabushiki Kaisha
4 1,775 Hewlett-Packard
5 1,760 Micron Technology
6 1,604 Samsung Electronics
7 1,601 Intel Corporation
8 1,514 Hitachi
9 1,310 Toshiba Corporation
10 1,305 Sony Corporation
Value of a college education?
The earnings differential between college graduates and those with only a high school degree has leveled off recently. There are several possible interpretations, as discussed by in this NYTimes article:
Another dynamic also undermines the value of a college degree, says David H. Autor, an economist at the Massachusetts Institute of Technology. While the college premium appears to be leveling off, the spread between the incomes of the highest-earning Americans and those in the middle expanded almost as fast in the 1990's as it did in the 1980's.
"If I may speak somewhat loosely, there continues to be rising demand for people who have very strong cognitive, managerial and communications skills," Mr. Autor said. "The vast middle, whether they are college educated or not, are not in that upper category of cognitive elite. The elite is college educated, but not all the college educated are those people."
In other words, nonlinear returns to the highly talented in our winner-take-all society, while ordinary people (college degree or not) struggle. And note that, despite recent attention, white-collar outsourcing is still too small a phenomena to affect these numbers, although that will change in the future.
A related statistic I heard in an economics of higher ed talk: after controlling for family wealth and academic performance (high school grades and SAT scores), there is very little difference in earnings between graduates of public and elite private universities. According to this data, the additional economic value of an Ivy League degree is less than the extra tuition paid!
Another dynamic also undermines the value of a college degree, says David H. Autor, an economist at the Massachusetts Institute of Technology. While the college premium appears to be leveling off, the spread between the incomes of the highest-earning Americans and those in the middle expanded almost as fast in the 1990's as it did in the 1980's.
"If I may speak somewhat loosely, there continues to be rising demand for people who have very strong cognitive, managerial and communications skills," Mr. Autor said. "The vast middle, whether they are college educated or not, are not in that upper category of cognitive elite. The elite is college educated, but not all the college educated are those people."
In other words, nonlinear returns to the highly talented in our winner-take-all society, while ordinary people (college degree or not) struggle. And note that, despite recent attention, white-collar outsourcing is still too small a phenomena to affect these numbers, although that will change in the future.
A related statistic I heard in an economics of higher ed talk: after controlling for family wealth and academic performance (high school grades and SAT scores), there is very little difference in earnings between graduates of public and elite private universities. According to this data, the additional economic value of an Ivy League degree is less than the extra tuition paid!
Wednesday, January 12, 2005
China FX reserves up $200B in 2004
Hmm... exactly how much of this inflow is actually sterilized by debt issuance? How much is diversified into euros? China's Treasury holdings were recently reported at only $180B. That means they either did a lot of hidden buying via intermediaries, bought a lot of agency debt, or both.
WSJ: "China's foreign-exchange reserves jumped more than $200 billion in 2004 to reach $609.9 billion at year end, as speculators betting on a rise in the local currency's value added to the effect of a widening trade surplus.
Last year's huge increase was the biggest surge in China's reserves in any single year -- indeed, it was bigger than China's entire reserves until 2001. The gain of $206.7 billion, almost half of which was registered in the last three months of the year, almost certainly will add to pressure on Beijing to let its currency appreciate, even though much of the increase was the result of speculative inflows betting on just such an outcome.
The figures, disclosed to Dow Jones Newswires by a Chinese central bank official yesterday, would have been even higher had China not used $45 billion in reserves to recapitalize two huge banks last year. China's foreign reserves constitute the second-largest such stash in the world behind Japan's.
Adding steadily to Beijing's money pot are China's robust exports. Yesterday, China's Ministry of Commerce reported exports rose 35.4% to $593.36 billion in 2004. That, in turn, pushed the country's full-year trade surplus to $31.98 billion, up 26% from 2003, despite rising import costs. Foreign direct investment, a further source of reserves, reached $57.55 billion in the first 11 months of the year, surpassing the $53.5 billion recorded for all of 2003. The full-year investment figure hasn't been announced.
Much of the additional reserves, some $95 billion, came from so-called hot-money inflows, says Dong Tao, chief Asia economist for Credit Suisse First Boston. These swell the reserves because China, to maintain its currency peg to the U.S. dollar, buys foreign currency that enters the country in exchange for yuan."
WSJ: "China's foreign-exchange reserves jumped more than $200 billion in 2004 to reach $609.9 billion at year end, as speculators betting on a rise in the local currency's value added to the effect of a widening trade surplus.
Last year's huge increase was the biggest surge in China's reserves in any single year -- indeed, it was bigger than China's entire reserves until 2001. The gain of $206.7 billion, almost half of which was registered in the last three months of the year, almost certainly will add to pressure on Beijing to let its currency appreciate, even though much of the increase was the result of speculative inflows betting on just such an outcome.
The figures, disclosed to Dow Jones Newswires by a Chinese central bank official yesterday, would have been even higher had China not used $45 billion in reserves to recapitalize two huge banks last year. China's foreign reserves constitute the second-largest such stash in the world behind Japan's.
Adding steadily to Beijing's money pot are China's robust exports. Yesterday, China's Ministry of Commerce reported exports rose 35.4% to $593.36 billion in 2004. That, in turn, pushed the country's full-year trade surplus to $31.98 billion, up 26% from 2003, despite rising import costs. Foreign direct investment, a further source of reserves, reached $57.55 billion in the first 11 months of the year, surpassing the $53.5 billion recorded for all of 2003. The full-year investment figure hasn't been announced.
Much of the additional reserves, some $95 billion, came from so-called hot-money inflows, says Dong Tao, chief Asia economist for Credit Suisse First Boston. These swell the reserves because China, to maintain its currency peg to the U.S. dollar, buys foreign currency that enters the country in exchange for yuan."
Tuesday, January 11, 2005
New Scientist and minimal length
New Scientist, a UK science magazine, covered our work on minimal length and quantum gravity. (Done while I was on sabbatical at Caltech.) You can compare the following summary to what I posted on this blog last November.
The smallest measurable length announced
27 November 2004. From New Scientist Print Edition.
PHYSICISTS have set a limit on the smallest length that can ever be measured - and any device that tries to beat the limit will be crushed into a black hole of its own making.
The finding is based on an analysis of interferometry, a technique that uses interference of waves to measure small lengths. Quantum theory says that the more accurate the measurement you want, the more massive the interferometer you need.
But Xavier Calmet, Michael Graesser and Stephen Hsu of the California Institute of Technology in Pasadena point out that any very massive interferometer would have to be spread over an extremely large region of space. Otherwise, the large mass concentrated in a small area would produce strong enough gravity to form a black hole, sucking in the interferometer.
But as the mass and the size are made ever larger to measure ever smaller lengths, the interferometer eventually becomes so big that its various components would not be able to interact fast enough for it to work, even using signals travelling at the speed of light.
Mathematically, these constraints lead to an instrument that can accurately measure only down to about 10-33 centimetres, a distance known as the Planck length (Physical Review Letters, vol 93, p 211101).
The smallest measurable length announced
27 November 2004. From New Scientist Print Edition.
PHYSICISTS have set a limit on the smallest length that can ever be measured - and any device that tries to beat the limit will be crushed into a black hole of its own making.
The finding is based on an analysis of interferometry, a technique that uses interference of waves to measure small lengths. Quantum theory says that the more accurate the measurement you want, the more massive the interferometer you need.
But Xavier Calmet, Michael Graesser and Stephen Hsu of the California Institute of Technology in Pasadena point out that any very massive interferometer would have to be spread over an extremely large region of space. Otherwise, the large mass concentrated in a small area would produce strong enough gravity to form a black hole, sucking in the interferometer.
But as the mass and the size are made ever larger to measure ever smaller lengths, the interferometer eventually becomes so big that its various components would not be able to interact fast enough for it to work, even using signals travelling at the speed of light.
Mathematically, these constraints lead to an instrument that can accurately measure only down to about 10-33 centimetres, a distance known as the Planck length (Physical Review Letters, vol 93, p 211101).
Pessimism of the intellect
Two must-read commentaries on the current account and macro environment by Brad Setser and Stephen Roach.
Roach: "The real federal funds rate was lowered into negative territory in 2002 and has only very recently moved back to the “zero” threshold. This marks the most protracted period of negative real short-term US interest rates since the late 1970s -- hardly a comforting comparison. Carry trades have become no-brainers for yield-starved investors, who can borrow for nothing at the short end of the curve and pocket the spread virtually anywhere else in the risk spectrum. Carry trades also become no-brainers for income-short American consumers, who can draw down income-based saving and use a very facile refinancing technology to extract newfound purchasing power from asset markets."
Setser: "Today's trade deficit is not only much bigger than our deficit back in the 1980s – when grown-ups like James Baker decided it was too big – it also is much riskier. The US back then had, more or less, as many external assets as liabilities. That is NOT the case now. Our liabilities exceed our assets, and by a substantial margin. Our net debt will be 27-28% of GDP at the end of the year.
Global rebalancing means that over time, the US needs to export more goods and services and less debt. Either that, or it will have to import a lot less. To me, this is common sense, not media misinformation. No country, not even the US, can run up its external debt forever."
Roach: "The real federal funds rate was lowered into negative territory in 2002 and has only very recently moved back to the “zero” threshold. This marks the most protracted period of negative real short-term US interest rates since the late 1970s -- hardly a comforting comparison. Carry trades have become no-brainers for yield-starved investors, who can borrow for nothing at the short end of the curve and pocket the spread virtually anywhere else in the risk spectrum. Carry trades also become no-brainers for income-short American consumers, who can draw down income-based saving and use a very facile refinancing technology to extract newfound purchasing power from asset markets."
Setser: "Today's trade deficit is not only much bigger than our deficit back in the 1980s – when grown-ups like James Baker decided it was too big – it also is much riskier. The US back then had, more or less, as many external assets as liabilities. That is NOT the case now. Our liabilities exceed our assets, and by a substantial margin. Our net debt will be 27-28% of GDP at the end of the year.
Global rebalancing means that over time, the US needs to export more goods and services and less debt. Either that, or it will have to import a lot less. To me, this is common sense, not media misinformation. No country, not even the US, can run up its external debt forever."
Monday, January 10, 2005
China's world beaters?
The Economist is pessimistic about China's prospects for producing world-class companies, despite their privileged access to domestic markets and capital.
"China has so far failed to build world-class companies. Even the natural monopolies and resources companies are mostly just big rather than particularly efficient. In manufacturing, technology and consumer areas, a few companies are groping towards international competitiveness, but none are there yet. Nor will China necessarily produce a Sony or a Samsung. “People assume it is just a matter of time before China develops world-class brands,” says Mr Gilboy. “But Chinese firms may not develop like Japanese or Korean ones did. China may be building a distinct model of capitalism with distinct firms.” While American firms broadly excel at breakthrough innovations, and Japanese ones at process and incremental innovations, “China capitalism may simply be best at making things a lot cheaper.” If so, China might do well to focus on building no-name component suppliers as Taiwan has, rather than home-grown brands as in Japan and South Korea."
"China has so far failed to build world-class companies. Even the natural monopolies and resources companies are mostly just big rather than particularly efficient. In manufacturing, technology and consumer areas, a few companies are groping towards international competitiveness, but none are there yet. Nor will China necessarily produce a Sony or a Samsung. “People assume it is just a matter of time before China develops world-class brands,” says Mr Gilboy. “But Chinese firms may not develop like Japanese or Korean ones did. China may be building a distinct model of capitalism with distinct firms.” While American firms broadly excel at breakthrough innovations, and Japanese ones at process and incremental innovations, “China capitalism may simply be best at making things a lot cheaper.” If so, China might do well to focus on building no-name component suppliers as Taiwan has, rather than home-grown brands as in Japan and South Korea."
Sunday, January 09, 2005
PIMCO commentary
Here is the latest from PIMCO's Bill Gross. One interesting comment: It is PIMCO’s opinion that central bank purchases in 2004 were the primary force in lowering 10-year Treasury rates from 4.90% to nearly 4.0% in October, while the Fed was in the process of raising short rates by 125 basis points. On the other hand I keep reading that China's central bank holdings are generally of short duration. I suppose the Japanese can afford to go out further on the yield curve: real interest rates in Japan are close to zero, so a 4.2% yield on 10y Treasurys doesn't look so bad. Also, the $700B in Treasurys they currently hold is only a small component of their national savings.
Friday, January 07, 2005
Moore's Law progress report
Moore's Law predicts exponential growth in the number of transistors on microchips, with a doubling time of roughly 1-2 years. As discussed here, the prediction continunes to hold for transistors but not necessarily for the overall performance of the chip, as clock speeds have lagged of late. There is some hope that through concurrency (multi-threading of processes), the performance gain can be made up, but this will require fundamental changes in software design.
Moore's Law is at the intersection of physics and economics. We haven't yet reached the point of fundamental physical limitations on chip performance, although we may be only a decade or two away (people have been saying that since Moore formulated his law). But perhaps economic factors are beginning to intrude - the rate at which new fabs are brought on line is determined in part by market demand for bleeding edge performance. Only a very small subset of the market runs applications that need a 4GHz chip.
Moore's Law is at the intersection of physics and economics. We haven't yet reached the point of fundamental physical limitations on chip performance, although we may be only a decade or two away (people have been saying that since Moore formulated his law). But perhaps economic factors are beginning to intrude - the rate at which new fabs are brought on line is determined in part by market demand for bleeding edge performance. Only a very small subset of the market runs applications that need a 4GHz chip.
Thursday, January 06, 2005
Asperger's syndrome and BitTorrent
Wired has a nice profile of Bram Cohen, the creator of BitTorrent. BitTorrent is a distributed P2P program that allows for sharing of massive files. Reportedly, it accounts for a third(!) of all bandwidth usage right now.
Bram, who was co-captain of the Stuyvesant math team in high school, is apparently part of the Autistic Nation: "Bram will just pace around the house all day long, back and forth, in and out of the kitchen. Then he'll suddenly go to his computer and the code just comes pouring out. And you can see by the lines on the screen that it's clean," Jenna says. "It's clean code." She pats her husband affectionately on the head: "My sweet little autistic nerd boy." (Cohen in fact has Asperger's syndrome, a condition on the mild end of the autism spectrum that gives him almost superhuman powers of concentration but can make it difficult for him to relate to other people.)
How long before O'Reilly publishes a book called Managing Asperger Coders?
Bram, who was co-captain of the Stuyvesant math team in high school, is apparently part of the Autistic Nation: "Bram will just pace around the house all day long, back and forth, in and out of the kitchen. Then he'll suddenly go to his computer and the code just comes pouring out. And you can see by the lines on the screen that it's clean," Jenna says. "It's clean code." She pats her husband affectionately on the head: "My sweet little autistic nerd boy." (Cohen in fact has Asperger's syndrome, a condition on the mild end of the autism spectrum that gives him almost superhuman powers of concentration but can make it difficult for him to relate to other people.)
How long before O'Reilly publishes a book called Managing Asperger Coders?
Risk premium and equity outperformance
As discussed previously, there are good reasons to expect that the equity risk premium will be less than 5% (its historical value over the last century) in the future. In the 19th century, stocks only outperformed bonds by 1.5%!
This is of course relevant to the current debate over privatization of social security. Below I've reproduced a figure from William Bernstein's site Efficient Frontier, which shows the probability of equity outperformance for a given value of the risk premium and an assumed historical volatility of about 17% for stocks. For example, if the risk premium is only 2% over the next 20 years, there is a 35% chance the equity portion of an individual account will actually do worse than if it were invested in treasuries.
Bernstein attributes the very different results of the 19th and 20th centuries to inflation. He claims that in the 19th century inflation was not understood to be a threat to bond returns. At the beginning of the 20th century, bond yields were 5%, which looked pretty attractive, as it was assumed to be a real rather than nominal yield. The inflation brought on by two world wars and the death of the gold standard was disastrous for bond holders. On the other hand, equity returns managed to keep pace with inflation (companies could pass increased costs on to consumers). As a consequence, investors bid up equities and devalued bonds. I still think there are obvious reasons (such as short-term volatility) for investors to demand a premium for holding equities. But a 5% equity premium is quite optimistic.
Bernstein: With hindsight we can see that the 5% stock-bond return gap in the 20th century was the result of a totally unexpected inflationary burst produced by the abandonment of hard money. You can’t abandon hard money twice, so a repeat is not possible. Though inflation might increase dramatically in the future, resulting in another high stock-bond return gap, it’s at least as likely that inflation will remain tame for the foreseeable future, producing nearly equal stock and bond returns. More importantly, we now live in a world where investors have learned to extract an inflation premium from bonds and to expect inflation protection from stocks.
This is of course relevant to the current debate over privatization of social security. Below I've reproduced a figure from William Bernstein's site Efficient Frontier, which shows the probability of equity outperformance for a given value of the risk premium and an assumed historical volatility of about 17% for stocks. For example, if the risk premium is only 2% over the next 20 years, there is a 35% chance the equity portion of an individual account will actually do worse than if it were invested in treasuries.
Bernstein attributes the very different results of the 19th and 20th centuries to inflation. He claims that in the 19th century inflation was not understood to be a threat to bond returns. At the beginning of the 20th century, bond yields were 5%, which looked pretty attractive, as it was assumed to be a real rather than nominal yield. The inflation brought on by two world wars and the death of the gold standard was disastrous for bond holders. On the other hand, equity returns managed to keep pace with inflation (companies could pass increased costs on to consumers). As a consequence, investors bid up equities and devalued bonds. I still think there are obvious reasons (such as short-term volatility) for investors to demand a premium for holding equities. But a 5% equity premium is quite optimistic.
Bernstein: With hindsight we can see that the 5% stock-bond return gap in the 20th century was the result of a totally unexpected inflationary burst produced by the abandonment of hard money. You can’t abandon hard money twice, so a repeat is not possible. Though inflation might increase dramatically in the future, resulting in another high stock-bond return gap, it’s at least as likely that inflation will remain tame for the foreseeable future, producing nearly equal stock and bond returns. More importantly, we now live in a world where investors have learned to extract an inflation premium from bonds and to expect inflation protection from stocks.
Wednesday, January 05, 2005
Extreme male minds and autism
The Essential Difference: male and female brains and the truth about autism by Simon Baron-Cohen
Another book on the holiday list. Why was I interested in this? Recently Asperger's Syndrome (AS), a form of high-functioning autism, has become the chic condition of choice for geeks worldwide. Yes, kids who in the old days were simply math or computer nerds are now self-identified (often with pride!) as having AS. Silicon Valley is full of these people. The rest of us are mere "neurotypicals" :-)
Baron-Cohen is head of the Autism Research Centre at Cambridge, and a professor of psychology. He claims that male brains tend to be better at "Systematizing" (organizing or analyzing things which exhibit order), while female brains are better at "Empathizing" (understanding what others are thinking or feeling). A fair amount of experimental data (pretty convincing) is presented, which supports the claim that the distributions of S-ability and E-ability are different in the male and female populations. (Incidentally, the effect of testosterone on brain development is well known, leading to significant variations in the actual sizes of various areas of the brain between males and females.) Baron-Cohen also gives plausible evolutionary arguments for how this came to be - a bit better than the "girls were selected to be good mommies, boys to be good hunters" story, but you get the idea.
The novel part of his theory is that the autistic mind is an example of an extreme male mind - one that is obsessed with systematizing and very bad at empathizing. In a particularly amusing chapter he profiles a famous mathematician (Fields medalist) and some physicists (Dirac, Newton and Einstein) who he claims likely have or had AS. He even quotes a female physicist working at CERN saying that her male colleagues lack social skills and are arrogant obsessives :-) Well, what can I say, it is all true. But it doesn't mean we all have AS...
Not to be missed are the fun tests at the back of the book, which measure your S and E quotients!
Another book on the holiday list. Why was I interested in this? Recently Asperger's Syndrome (AS), a form of high-functioning autism, has become the chic condition of choice for geeks worldwide. Yes, kids who in the old days were simply math or computer nerds are now self-identified (often with pride!) as having AS. Silicon Valley is full of these people. The rest of us are mere "neurotypicals" :-)
Baron-Cohen is head of the Autism Research Centre at Cambridge, and a professor of psychology. He claims that male brains tend to be better at "Systematizing" (organizing or analyzing things which exhibit order), while female brains are better at "Empathizing" (understanding what others are thinking or feeling). A fair amount of experimental data (pretty convincing) is presented, which supports the claim that the distributions of S-ability and E-ability are different in the male and female populations. (Incidentally, the effect of testosterone on brain development is well known, leading to significant variations in the actual sizes of various areas of the brain between males and females.) Baron-Cohen also gives plausible evolutionary arguments for how this came to be - a bit better than the "girls were selected to be good mommies, boys to be good hunters" story, but you get the idea.
The novel part of his theory is that the autistic mind is an example of an extreme male mind - one that is obsessed with systematizing and very bad at empathizing. In a particularly amusing chapter he profiles a famous mathematician (Fields medalist) and some physicists (Dirac, Newton and Einstein) who he claims likely have or had AS. He even quotes a female physicist working at CERN saying that her male colleagues lack social skills and are arrogant obsessives :-) Well, what can I say, it is all true. But it doesn't mean we all have AS...
Not to be missed are the fun tests at the back of the book, which measure your S and E quotients!
Tuesday, January 04, 2005
Christmas reading - Kahneman and Tversky
I realize that the holiday season is over (boy do I realize it, since I am back in the classroom as of today), but I thought I would report on a couple of books I read over the break.
Choices, Values, and Frames
by Daniel Kahneman and Amos Tversky
This is a collection of papers on cognitive psychology as applied to economics and decision making. Kahneman and Tversky were pioneers in what is now known as behavioral economics. The papers are clearly written and offer a nice introduction to this field.
As you can tell from some of my previous posts mocking the idea of strongly efficient markets, I am not myself a big believer in the rationality or analytical power of individuals who make up markets. However, this does not mean I doubt the power of markets as aggregators of information, and on this subject I highly recommend Surowiecki's book The Wisdom of Crowds. Certainly, it is not excluded that a machine could function usefully even if many of its subcomponents are faulty :-)
I won't try to summarize everything in the book, which at minimum provides a nice compendium of cognitive quirks uncovered in surveys and laboratory observations. One that I found quite interesting is the prevalence of risk aversion, extending even to very small wagers. The typical person's utility function, as extracted from experimental observation, is not at all linear even for small amounts at risk - the pain of a loss exceeds the pleasure of a gain of equal size.
It seems reasonable to assume that individual utility functions are logarithmic - a gift of $1000 brings proportionally less pleasure to a billionaire than to a millionaire. But there is good evidence that this is not so, and indeed M. Rabin, in one of the papers, shows that the aversion to small losses cannot be accommodated by such a model of utility. It seems that our brains constantly set reference points ("zero points") relative to which we measure loss or gain.
If indeed our brains constantly (say on monthly to yearly timescales) reset their financial zero points, and are naturally risk averse, then volatility itself is a painful phenomena. One interesting idea of Rabin's is that this explains the (unnaturally?) high value of the equity risk premium.
In my opinion, investors have been trained in recent decades to believe that small losses are only temporary and that equity markets almost always go up over the long run. This makes them more resistant to loss aversion and leads to a smaller equity risk premium (and correspondingly high P/E ratios).
Choices, Values, and Frames
by Daniel Kahneman and Amos Tversky
This is a collection of papers on cognitive psychology as applied to economics and decision making. Kahneman and Tversky were pioneers in what is now known as behavioral economics. The papers are clearly written and offer a nice introduction to this field.
As you can tell from some of my previous posts mocking the idea of strongly efficient markets, I am not myself a big believer in the rationality or analytical power of individuals who make up markets. However, this does not mean I doubt the power of markets as aggregators of information, and on this subject I highly recommend Surowiecki's book The Wisdom of Crowds. Certainly, it is not excluded that a machine could function usefully even if many of its subcomponents are faulty :-)
I won't try to summarize everything in the book, which at minimum provides a nice compendium of cognitive quirks uncovered in surveys and laboratory observations. One that I found quite interesting is the prevalence of risk aversion, extending even to very small wagers. The typical person's utility function, as extracted from experimental observation, is not at all linear even for small amounts at risk - the pain of a loss exceeds the pleasure of a gain of equal size.
It seems reasonable to assume that individual utility functions are logarithmic - a gift of $1000 brings proportionally less pleasure to a billionaire than to a millionaire. But there is good evidence that this is not so, and indeed M. Rabin, in one of the papers, shows that the aversion to small losses cannot be accommodated by such a model of utility. It seems that our brains constantly set reference points ("zero points") relative to which we measure loss or gain.
If indeed our brains constantly (say on monthly to yearly timescales) reset their financial zero points, and are naturally risk averse, then volatility itself is a painful phenomena. One interesting idea of Rabin's is that this explains the (unnaturally?) high value of the equity risk premium.
In my opinion, investors have been trained in recent decades to believe that small losses are only temporary and that equity markets almost always go up over the long run. This makes them more resistant to loss aversion and leads to a smaller equity risk premium (and correspondingly high P/E ratios).
Saturday, January 01, 2005
Obstacles to China development
The possibility of social unrest in China due to widening inequality has been widely discussed. Here is some recent coverage from the Times.
But just as problematic is the vast misallocation of resources resulting from local government corruption, lack of transparency and absence of rule of law (i.e., "crony capitalism"). See here for an example involving the Apex scandal and export of TVs and DVD players. Apex is one of the largest distributors of DVD players and TVs in the US, and is primarily responsible for driving the price of DVD players below $50 dollars. Now it appears that Sichuan Changhong Electric Appliance, their main supplier, will report as much as $500M in losses due to lack of payment from Apex, stretching over a year. How could Apex get away with this? Who was paid off? The Times suggests that a Party boss and former Changhong executive was involved and has been sacked over the affair.
The head of a leading research institute in Beijing once said to me in this regard that "hardware is easy, software is hard" - meaning that it is easier to build factories, roads and airports than to implement a functioning market system and civil society with transparency and rule of law. The transition from a low-trust society (where the people don't trust their government, or even their neighbors) to a high-trust society (where things like the financial and legal systems are expected to work, and do) is difficult.
But just as problematic is the vast misallocation of resources resulting from local government corruption, lack of transparency and absence of rule of law (i.e., "crony capitalism"). See here for an example involving the Apex scandal and export of TVs and DVD players. Apex is one of the largest distributors of DVD players and TVs in the US, and is primarily responsible for driving the price of DVD players below $50 dollars. Now it appears that Sichuan Changhong Electric Appliance, their main supplier, will report as much as $500M in losses due to lack of payment from Apex, stretching over a year. How could Apex get away with this? Who was paid off? The Times suggests that a Party boss and former Changhong executive was involved and has been sacked over the affair.
The head of a leading research institute in Beijing once said to me in this regard that "hardware is easy, software is hard" - meaning that it is easier to build factories, roads and airports than to implement a functioning market system and civil society with transparency and rule of law. The transition from a low-trust society (where the people don't trust their government, or even their neighbors) to a high-trust society (where things like the financial and legal systems are expected to work, and do) is difficult.
Bandwidth costs and Internet broadcasting
I was researching the cost of bandwidth recently. Some interesting numbers I uncovered: backbone transport cost is $100 per month per Mbps, or about 30 cents per GB. ISPs and hosting services charge a bit more than this per GB, but as little as $.50 per GB. The bandwidth cost of servicing a typical residential cable or DSL broadband subscriber is only about $2 per month, so potential margins are large.
Mailing a DVD (4.8GB of data for the cost of a postage stamp) is still a cheaper method of data transfer than the Internet - albeit slower! When will NetFlix's inventiory management innovations become redundant due to Internet delivery of movies? Now that 50% of US Internet users have broadband, it will only be a few years before a similar business can be built around delivering movies directly over the wire. At 100kbps sustained, it takes 10^5 s - about a day - to download a movie.
What about running your own TV or radio station from your Web server? Even if bandwidth costs drop another order of magnitude, we'll still need distributed P2P like BitTorrent to make it affordable for individuals. BitTorrent stores copies of a file on multiple (volunteer) servers, and distributes the bandwidth burden by allowing a user to download via multiple streams. (It has been reported that BitTorrent alone currently accounts for about a third of all bandwidth usage!) Very soon, content distribution will be revolutionized by distributed P2P, with indie TV shows distributing their product via the Internet.
Mailing a DVD (4.8GB of data for the cost of a postage stamp) is still a cheaper method of data transfer than the Internet - albeit slower! When will NetFlix's inventiory management innovations become redundant due to Internet delivery of movies? Now that 50% of US Internet users have broadband, it will only be a few years before a similar business can be built around delivering movies directly over the wire. At 100kbps sustained, it takes 10^5 s - about a day - to download a movie.
What about running your own TV or radio station from your Web server? Even if bandwidth costs drop another order of magnitude, we'll still need distributed P2P like BitTorrent to make it affordable for individuals. BitTorrent stores copies of a file on multiple (volunteer) servers, and distributes the bandwidth burden by allowing a user to download via multiple streams. (It has been reported that BitTorrent alone currently accounts for about a third of all bandwidth usage!) Very soon, content distribution will be revolutionized by distributed P2P, with indie TV shows distributing their product via the Internet.