Posts filed under ‘Economy’
Private equity and the subprime crisis (bad news that could be good after all)
The subprime crisis has arrived. Yes, many anticipated so. That’s what happens when economy depends on expectations. They take some time to change and, when they change, they do it abruptly. Like those subprime mortgages that have transformed from “hot products” to “hot potatoes”.
Overall is not a matter of solvency but liquidity. I agree, tell that to those that will not be able to afford the mortgages, maybe up to 500.000 people in the US. But investors do not worry much about them. Investors just get scared and they stop pouring endless capital… until they start to do the same somewhere else.
Because companies still report record earnings and the price of gold has been rising non-stop. That means that the machine is still working.
But let’s not be too complacent. A wider crisis can still arise. If gold is “hot”, ABS are cooler than ever. ABS are asset-backed securities, financial products made up of mortgages and things alike that are covered by a real asset, such as your home. These are a way for banks to get cheap financing and externalise risks, because the default risk is transmitted by the ABS, while it wouldn’t be with debt, for instance.
If banks get increasingly difficult to finance, they will transmit this additional cost to companies and consumers. And that’s an entry point to generate a widespread crisis. Central banks should add additional liquidity to the system by lowering rates, but that seems unlikely given their current policies.
But, what about private equity? Now it will be more difficult for them to get cheap capital to finance, that’s for sure. But that doesn’t mean they have no future. On the contrary, they are now more needed than ever, because they are the ones to provide that leaning, that additional shakedown that companies needed in times of more expensive credit.
Remember, there’s much more to private equity than leveraged buy-outs, they have an important role in the markets, and that means they have an important role to play in this new situation.
PD: I read this morning in “The Economist” that the US were thinking of “relief measures” for the crisis. Then I changed to a Spanish newspaper and read about the Popular Party (centre-right and opposition and presumed liberal) to propose the right not to pay mortgages during a year for the unemployed. Alarmed by both news I couldn’t help the thought: regulation must ensure that the system is not abused but, let the market regulate itself. Although some regulations will be painful, it’s the most effective way we’ve come to know.
Blackstone going public… not so well (at least something is coming back to markets)
My readers (thank you for being there) already know that Blackstone is a private equity firm that I like and I’ve been following lately (See China and Blackstone: bad news for capital markets, good news for private equity).
I’ve always visualised private equity firms as a way to avoid the market’s constraints, and the firm’s constraints also, to be able to make longer term moves in order to ensure efficiency and the emergence of sunk benefits inside the firm (See Defensive strategies from private equity).
The funny thing is to see how a private equity firm just decides to go public. In any case, makes a lot of sense to me. At least the market recovers part of what has been taken off it. ($4.13 billion are a nice prodigal son to welcome home)
And Blackstone decided to do just that and went public last Friday.
Graph source Yahoo Finance
This graph is from IPO-day. If you read the news, it was a success, as the PR guys and gals are saying: biggest US IPO in the last four years, executives going mega-rich and all that stuff.
And I concur that it was a success. But not a wild success: a mild one.
In the picture, the trade for Friday: the share ended up at $35.06, far higher than the initial price of $31, a 13% more… of course it went up, it was already over-subscribed. But, take a second look, it didn’t go that far up. The Fortress Investment Group went 33% up in its IPO last February, and it wasn’t as sexy or hyped as Blackstone.
Things are changing. As I have also written before, cheap money is going scarce. (see Rates keep raising: is this the end of cheap money?) And maybe we’ve reached the peak. Bond’s yields are going up too.
Let’s take a peek at the market:
Graph source Yahoo Finance
The graph is the Dow Jones Industrial Average Index over the last year. The two curves below are the Relative Strength (RSI) and the Money Flow (MFI).
The RSI measures the internal strength, the momentum, and it’s indicative when the security reaches a high and the signal fails to reach one. It’s not as low as it was in March’s crisis, but it’s in the second lowest for the last year.
The MFI also measures momentum but takes into account volume as well as price. In this case it has shown repeatedly how the market was loosing strength, thus slowing the slope, so there is a divergence there. In any case it would be worrying if this signal went below 20%, which has not happened.
But my point is that things are not as bright as they were before. And probably things will be harder from now on. If these guys were discounting new highs, they could have waited for a better moment. But they decided to go in now. There must be a reason for that. Behind the curve probably we will find a bumpier road, not the accustomed highway they’ve enjoyed until now.
And, just another thought, another interpretation from a different perspective: is it sustainable that private equity firms enjoy a 15% tax rate while public companies are at 35%? Doesn’t seem quite fair. There’s a hard debate on this and proposed changes on legislation on the way… is Blackstone equity already discounting the conclusion of the debate? (or at least the uncertainty)
Last food for thought today: KKR has also announced it will go public. (yummy, yummy)
The South Sea Company (or how Sir Isaac Newton spurned the dismal science)
Some days ago I started writing about bubbles with the post Tulipmania, XVIIth century. Today I want to resume this journey throughout the major bubbles of the economy. Hopefully we’ll reach some conclusion together (I already have thought of some, and some are unexpectedly positive), or even see some bubble burst (probably).
We jump is from 1593 to 1711, from the Netherlands to England: the South Sea Company.
But the story begins somewhere else, earlier, with this king that was said was under a spell:
It’s 1700 and we are in Spain. King Charles II (Carlos II el Hechizado) has just died. He has been ill for almost all his life. He was 38, but looked much older.
But he has been the king of the biggest empire in the XVII century. An empire spread around the world that has splashed Europe around with his colors. An empire that imported tons of precious metals and discovered that the excess of currency also meant higher prices (hyperinflation). An unsustainable empire, thought to be very rich, but nonetheless an aging empire.
But Europe’s bound to change a lot after Charles II. Different powers were pushing at each other. And the rivalry of two families: the Habsburgs (Charles II was one of them) and the Bourbons.
And the prey is the Spanish Empire in Europe, not only Spain but also the Low Countries and parts of Italy. And, as vultures, the different European nations take sides in the Spanish Succession War.
The Bourbons win this war in Spain, but not in Europe. The initial plan had been to unite Spain with the emergent France, but Phillip V of Spain is forced to resign his post in the French line of succession.
He retains Spain’s overseas possessions but renounces to the Spanish Netherlands and the Spanish Italy both to Austria and Savoy, and Gibraltar and Minorca to Great Britain. France also cedes many colonial possessions overseas, but their borders are not changed.
All this is written and signed in the Treaty of Utrecht, 1713.
The South Sea House in Threadneedle Street
Why is this important for a company like the South Sea?
The company is established in 1911 by the financiers John Blunt and George Caswall, backed by Robert Harley, Lord Treasurer. It’s a time of war. The company is granted exclusive trading rights with South America if they take over the national debt caused by the war and consolidate it. Somehow it’s established as a sort of parallel organisation to the Bank of England.
After the war Britain is in debt for more than £10 million. (yes, 1713′s Pounds, not 2007′s). All that debt is funneled through the company transforming short-term debt into stock. In exchange the government is committed to paying £576,534 perpetually, that is roughly a 6% return.
But a trade company needs more than an annuity to exist. That is also provided by the Treaty of Utrecht. In it is also established that the Kingdom of Great Britain and Ireland will be able commerce with Spanish South America (something that they already discounted when founding the company). The South Seas company is able to send one trading ship each year.
Astonishingly, the company fails to do any trade for the first four years. Nonetheless it has the backing of the British Government, which soon converts a further £2 million in stock. No actual business, but a promise of a bright future (sound familiar?).
The company is also granted the exclusivity over the Spanish Asiento. That means being able to sell 4.800 slaves per year to the Spanish colonies. In 25 years they make around 70 voyages and sell 30.000 slaves. Only 4.000 perished in the journeys: that means being quite efficient for a slave trader.
Stocks going up…
But the company is not good enough at trade. What they are increasingly good is into transforming public debt into shares. And they manage to give away enough shares to important people (and rebuy them when they have increased enough) so that most politicians are interested in supporting and backing the South Seas Company. That is, to drive value up.
1719 is a good year for the South Seas company. They offer to buy half of the British national debt: £15 million. That means £15 million more in shares. But demand’s pace keep up. There’s a huge interest in their shares. After all they continuously rise and lucky owners feel they are richer every day.
1720 is going to be known as the bubble year. Not only will witness the skyrocketing of the South Seas but also the appearance of many similar ventures. The price per share will go from £100 to £1,000. People of all kinds will buy, selling whatever they have, going into debt, it’s the South Seas frenzy!
The fall follows the rise
The last idea that the company has is to lend people money to buy the shares. But the money has to be returned. And there is no other way to return it than selling shares again. Until it all collapses and the shares fall back to £150 in september. A great loss for most investors. And from that to obliteration.
Sir Isaac Newton
What about Sir Isaac Newton? Well, he won a lot of money with the South Sea when he sold it, but the shares kept rising and rising. Until he couldn’t resist the temptation to buy again. At the highest price. In the next week they plunged. He lost £20,000.
I can calculate the movement of the stars, but NOT the madness of men
Jonathan Swift also lost a fortune. He wrote Gulliver’s Travels, a satire about the British society. The cons fled somewhere else with their fortunes but, for Britain, the consequences of the crash lasted for a century.
Defensive strategies from private equity (spin-yourself-off)
Those of you who read me know my ideas about private equity and how it has become an increasingly efficient way to invest the “big bucks”. I wrote about this in China and Blackstone: bad news for capital markets, good news for private equity.
I have to confess I like the concept of private equity. Although private equity firms probably wouldn’t considering hiring me, I’d hire them to increase efficiency. Their whole business is about efficiency gains: buy some under-performing firm, use your credibility to increase debt to pay the buy-out, make it perform again. If the gains are similar to the costs, the company is yours… *for free*.
Of course I’m exagerating. That’s a simplification, but, for comparing purposes, what happens if you compare their strategy to the diversification strategies undertaken by big companies? We have extra resources, we are not really interested in giving them away to our investors, or owners, so we are going to buy some business out of our core knowledge and know-how to have less risk and at the same time less yields.
Why should anyone do that? Well, managers would say there are synergies to be gained, but, as you know, sometimes those synergies never make it out of the power-point file.
The real reason to do that is that the managers need to keep busy, and need content to present in their next shareholders meeting, probably speaking about another business they don’t know anything about. (Fortunately, neither the shareholders)
Are they paid to do this? Are they suitable to do this? Hell, no!
Not so long ago, they were pretty relaxed and calm because nobody would object anything to that strategy. Even shareholders didn’t see that it was easy to reduce their risk just diversifying investments in different companies instead of diversifying core businesses.
If the investor can diversify by himself, companies shouldn’t try ventures alien to their business.
Then, why were the big companies so unperturbed just doing that? Because they were huge. Or at least too big for hostile takeovers.
And then came KKR with RJR Nabisco (See article about KKR here), and Cerberus with Chrysler (See article about Cerberus here), starting a series that could end with ABN Amro or who knows what. Being huge is not safe anymore.
A new signal emerges from markets. It’s the end of diversification. It’s time to concentrate on your core business. For public companies there’s only one protection strategy for private equity. And it’s no longer to be huge, now you need to be efficient instead.
Barbam propinqui radere, heus, cum videris, praebe lavandos barbulae prudens pilos
(in latin, if you neighbour is being shaven, do get your beard ready)
*Efficiency will save you from private equity*
Got an interesting non core business? Let it go. Otherwise private equity will come for you, and spin it off you.
Inside the non-efficient companies lie a lot of unused resources that justify the gains private equity need as an excuse to assault them. If only those companies could use those same resources for protection…
But that would mean being efficient again. That would mean ruthless reestructuring. That would mean hard and painful decisions. That would mean having to face change, sometimes radical change. That would mean challenging established authority. In short that would mean working more and better.
One last problem about leaning and trimming yourself: why do it yourself when private equity can do it more efficiently than you? (And market seeks efficiency, somehow)
Rates keep raising: is this the end of cheap money?
Yes, interest rates are soaring. The ECB raised rates two days ago 25 basic points to 4% as expected. That was the highest rate in six years. You know how I like using images, here is the picture of the last year:
Why has the ECB risen the rates again? Fear of inflation as usual. Europe has been growing faster than the US and that means that industries will approach production peaks and probably companies will face more pressure to drive salaries up. But only probably, because that hasn’t happened yet. The European Central Bank bets to put pressure down even before it’s needed. Or is it?
We’ve seen so much liquidity lately, so many money. The quantity of money has been growing steady, more than ever. You can see it in this graph I made with data from the US Federal Reserve, 1959 to 2006:
M2 and M3 are common metrics or measures for money. While M2 represents physical currency, bank reserves, current accounts, saving accounts and small deposits, that is the money that is available to domestic economies, M3 also includes bigger certificates of deposits (above $100,000), Eurodollars and repos.
You might ask, where has that liquidity gone? That’s why I chose to draw the red curve: M3 without M2, that is the money that is not in the hands of domestic economies. As you can see it has been growing at a hectic pace. This is the money that has been refuelling the economy, making stocks soar, gone into funds, hedge funds, private equity or debt.
So maybe, after all, central banks were not thinking of us when raising taxes, but in those huge quantities of money that are not in the hands of domestic economies.
And with money being more expensive, we’ll probably see trouble in junk bonds, too-risky capital and excessive leverages, subprime mortgages, the riskiest places where the bulk of the money has gone to.
Rising taxes mean that the most vulnerable parts of the economy may suffer. We’ll see the definitive end of many bubbles, maybe mortgages, junk bonds, overpriced shares or excessive debt can be the match that lightens the next crisis. And that can mean trouble for our pockets too.
One thing for sure: rates will keep soaring, I have no doubt. One way to know what the market thinks about it is using the Euro Interbank Offered Rate, Euribor. If you follow that link you can get the daily Euribor rates in a range from one week to twelve months, that is the rates that first class Euro banks offer each other. Euribor is representative enough of the Euro money market.
The red curve was in January, the blue curve is now. So far the market has been predicting well the increases for the last six months. The arrow marks the value for borrowing Euros for six months six months ago and compares it to the actual value. As you can see, it’s rather close to the current value.
Well, in fact it’s higher because there is a smoothing effect: when you are paying to borrow for six months you are paying higher (or lower) for the last months, but closer to the current rate for the first months, so you get an average of both.
So, looking at the blue curve, the market predicts additional increases for the next months. And the slope is even steeper slope, that means no sign of stopping to be seen in the next year. The rates will keep rising on the long run.
It’s been ten years from the last monetary crisis. Maybe the next one is getting closer. That would have central banks change their mind about rates.
Cerberus Capital Management: another style for private equity
A few days ago I wrote about KKR and the three men behind that acronym. Now it’s the time for another company that lies in the private equity niche too, but, as you will see, plays its cards quite differently. In this article I’ll focus on the difference between them.
the original Greek Cerberus, a dog with three heads that guards the world of the dead and won’t let you in
Cerberus Capital Management was news just three weeks ago, when they announced they’d buy Daimler’s 80.1% stake in Chrysler for $7,400 million. Three months before the company had announced the laying off of 13,000 employees, after the red tape exceeded $1,500 million for 2006.
Not very good times for Daimler and Crysler. That was the end of a transatlantic marriage that lasted since 1998 and cost $36,000 million.
As you know, good times for private equity, bad times for inefficiencies and for corporate social responsibility: more laying offs ahead. More trouble in the Motor City: Detroit. And of course unions abhorring of letting private equity in, unions such as the United Automotive Workers and their leader: Ron Gettlefingers, warning about the dangers.
worried about the takeover? when this man speaks, Motor City listens
But something strange happened. Ron Gettlefingers, after some months sending the leave-Chrysler-alone message decided to back up the take over. Why? Who convinced him and how?
this is the man from Cerberus that convinced Gettlefingers: John W. Snow
What did Snow promise? Three things: to keep the same management team (I’m not sure that is a good idea after $36 billion having gone down the drain), to keep his three brands (well, without further analysis, looks sensible to think about consolidating the strongest only), and no further lay-offs and contract negotiations to be held this summer with the unions (which doesn’t mean that they’ll succeed either).
Will they be able to deliver? who knows.But that’s not the point.
They have credibility or, at least, they have a very different style. Cerberus managers are not perceived as elitist billionaires -and that’s a difference with KKR. Cerberus founder Steve Feinberg was son for a steel’s salesman, graduated in politics in Princeton while playing a lot of tennis. It has been said of him: “While other hedge-fund managers are collecting fine French wines and flying around in private planes, he drives a Ford truck and drinks Budweiser.” (Follow this link to a Businessweek article for the source)
most appreciated piece of art in Cerberus headquarters
It is said that the most valuable piece of art that is stored in Cerberus headquarters is a poster by the Fugees. Feinberg himself drives a pickup and wants no personal publicity. Half of their staff are ex-managers, a big number when compared to other companies that heavily relay on consultancies.
remember the one on the left? from US vice-president to Cerberus vice-president
Dan Quayle is also in Cerberu’s team as vicepresident. Not famous for his literacy or his perfect spelling, but close to the people. The same style that has made George W. president twice.
So, which are the main differences between the way of doing business of KKR and Cerberus?
- Cerberus are perceived as peacemakers, not as hard negotiators. Got nervous union leaders? they just hop on a plane and talk face to face plain conversations, making trust, opening bridges. As Buzz Hargrove, president of the Canadian Auto Workers (CAW) said on Feinman, “He gave us all letters that said there will be no job losses. He was very genuine, not some highfalutin billionaire. It was real talk.”
- And a financial difference: they don’t use leveraged buy-outs. That way the cost of borrowing money keeps lower. And, guess what, they talk to creditors too, giving them a lot of information and letting them participate. That makes trust too, and the more the trust, the less the borrowing costs also.
- Not worried about quick returns either. Let things take their time.
So, money is not everything, is it?
Economy: art or science?
If you have read me before you know that one of the things I’ve been asking myself is whether Economy is a solid enough science to lead us to the truth, whatever that might be. I thought about it in the previous post “Is Economy as a science solid enough to define what’s true and what’s not?“, and end up talking about the Lucas critique.
Well, I have to say I began being sceptic, thinking that Economy was not stable enough to be called a “science”, but slowly changed my mind.
And like a coin, now I think there are two sides to Economy: science and art.
The “science side”, is it solid enough to reach the truth? Yes it is. We’ve been discovering a series of laws, economic laws, that deserve being qualified as “natural laws”, that rule the production and distribution of wealth. It’s just like Chemistry that is able to understand and describe how the elements interact and combine. The applications? Those can be done in so many different ways…
And there is the “art side”, a side that Chemistry doesn’t have (maybe I should rethink that too). In Economy the distribution of wealth can be designed in so many different ways. For sure Rawls and Nozick would do it in two very different ways. But not only them but each of us would be creative in our own way. As in every art, some might even be better artists than others.
Because those natural laws that work from the shadows even made perfectly (?) planned economies to have cycles, as Kitchin, Juglar, Kuznets, Kondratev or the cluster innovations of Schumpeter –yes, again- and Mensch. Even with the cycle denial by Milton Friedman, we still have bubbles: technological bubbles, housing bubbles, internet bubbles, biotech bubbles, stock bubbles (I think we could be in one of those now) again and again.
painting political ideas in a blank canvas
Good artists will try, from their posts, to use their tools (call them fiscal policies, monetary policies or whatever you wish) to create something nice that responds to their personal perspective or even to their ideals. Sometimes seeking social justice –whatever its definition might that be –sometimes just seeking self profit –a great way to create wealth too-, or just seeking to predate other’s resources.
Now to the conclusion: the part of Economy that is a science will help us understand the world, drawing solid conclusions, reaching objective truths. The part of Economy that is art will let us use those basic laws to build something of our own, to create.
Economy’s nature is a dual one.
Kohlberg, Kravis & Roberts, the three men behind private equity’s star KKR
As you probably know, private equity firms are hot. And as they get more and more funds (remember how the Chinese government decided to invest in Blackstone) they become even more desirable.
KKR used to be the Holy Grail of private equity. KKR stands for Kohlberg, Kravis & Roberts and was founded in 1976 by Jerome Kohlberg, Henry Kravis and George Roberts. KKR specialised in leveraged buyouts and starred with the buy of RJR Nabisco in 1988 for $31.4 billion. There’s a must-read book about this buyout: Barbarians at the gate, by Bryan Burrough and John Helyar. And a movie too.
Blackstone has broken that record this year- yes 2007- and gone from princess to queen, but that’s a story for another day.
You could say that they used junk bonds to buy underperforming companies, reworked their balance sheets, and sold them for profit, maybe as a whole, maybe not.
But who where those entrepreneurs that decided to create KKR? Where are they now?
The first, Jerome Kohlberg, was born in 1926. Unsurprisingly, he was working with Roberts and Kravis in Bear Stearns, worldwide investment banking and securities trading and brokerage firm. He left KKR in 1987 –that is one year before the Nabisco takeover- but he didn’t retire until 1994 when he created the Kohlberg Foundation. His wife has a restaurant, the Flying Pig, in Mount Kisco, NY. His fortune is approximately $1.2 billion.
Henry Kravis was born in 1944. Economist and Columbia MBA, in KKR he was the key to developing the LBO, leveraged buyout, concept, acquiring corporations they thought were under their potential, putting 10% of the price and financing the rest through junk bonds. (At that moment the concept of junk bond was still undefined, they were just high-yield bonds). The concept included selling whatever assets that could be valuable and leaning the company to a maximum before selling again with huge profits. He directed the Nabisco takeover after Kohlberg’s parting, creating the legend for KKR. He also participated in buying huge brands like HCA Inc., Texaco, Gillette, Playtex, Beatrice, Safeway, Borden and Samsonite. He is a prominent Republican and a strong supporter of G. W. Bush. (What a coincidence: Nabisco also began donating great amounts to the Republicans after the takeover) His fortune is approximately $1.5 billion.
George Roberts was born in 1945. Cousin of Henry Kravis, Law Graduate. Mentored too by Jerome Kohlberg in Bear Sterns, he cofounded KKR, participated in the Nabisco takeover –he is one of the main characters of Barbarians at the gate- until he exited in 1987. He’s been active ever since, participating in the Toys’r'us takeover by $6.6 billion with Bain Capital this year and SunGard Data Systems for $10.6 billion with Blackstone. His fortune is approximately $2.5 billion.
Well, he is the richest of all three so maybe he has something to tell. This text is from his acceptance speech at the 1998 Man of the Year’s award from the Culver Military Academy:
“I’m often asked by people, especially younger people, what do you have to do to be successful. And I assume they’re asking not what you have to do to make money, but what do you have to do to be a successful individual. Coming out here, I jotted down several examples that I’d like to share with you.
“You’ve got to work hard at whatever you do. So if you’re going to work hard and put everything you have into what you’re doing, you better find a job and a career that you love to do, because if you don’t you have no chance.
“Set your goals. Set goals that are unrealistic in some cases. Be prepared to be disappointed. One of the goals I set for myself when I came to Culver was to get into Yale. I got turned down. One of the goals I set for myself when I graduated from CMC was to get into either Stanford Law School or Stanford Business School. I got turned down. Set your goals high; reach, that way you improve our muscle tone. Don’t be afraid to fail. Our society won’t penalize you if you fail honorably, and by that I mean with integrity and honesty. Everyone who has done anything in life has failed at something. And there will be nobody in this room who is any different.
“Keep a sense of humor, that’s probably the most important thing. Be prepared to laugh at yourself a little bit, your mistakes. And when things really get tight and tense and everything else, laugh a little bit.
“Keep a perspective of what’s really important. For me, that’s been my health, the health of my family, and those intangible things that don’t involve material objects.
“Raise a family, because that’s the only way you’re going to learn to love somebody or some group more than yourself.
“Rely on yourself with both your brain and your heart. Don’t blame others for the mistakes that happen. Learn from them yourself and go on.
“And lastly, help others that are less strong and less fortunate than yourself, because you will get back many, many, many fold what you have done for yourself.”
The 10 biggest tech companies
Which are the biggest tech companies? With that much hype, sometimes it’s hard to know. But there are ways to guess a list. I’ve decided to build one myself. Couldn’t be otherwise, I just let the market decide. I chose NASDAQ, and today for market capitalisation. I’ve linked all names with their websites. That’s the list. Some of the names might come as a surprise.
That’s what investors say they are worth:
| NASDAQ 100 | |||
| # | Company | Value | B$ |
| 1 | Microsoft CP | 291,6 | B$ |
| 2 | Cisco | 154,94 | B$ |
| 3 | Intel CP | 128,75 | B$ |
| 4 | 111,92 | B$ | |
| 5 | Oracle Corp | 98,91 | B$ |
| 6 | Apple Inc | 98,28 | B$ |
| 7 | Qualcomm Inc | 72,25 | B$ |
| 8 | Amgen Inc | 63,26 | B$ |
| 9 | Dell Inc | 59,04 | B$ |
| 10 | Comcast CP | 56,35 | B$ |
| 11 | Ebay Inc | 44,53 | B$ |
| 12 | Yahoo! | 38,41 | B$ |
| 13 | Gilead Sciences | 34,08 | B$ |
| 14 | Teva Pharm Industries | 31,92 | B$ |
Logit models in Econometrics and bit entropy: there’s something going on here
First Econometrics
One of the cases that we face in econometrics is when the response variable is qualitative. In the simplest case, the response can be either 0 or 1. Some examples:
- Given some parameters about a person: will he vote democrats or republicans? will he subscribe to some magazine? will she leave her job if pregnant? Will the student decide to cheat? Will she vote at all?
- Or given some parameters about a bond, how will it be classified? it will surely depend on volatility, leverage, assets…
- A teacher wants to know if a student will pass his exam.
- A financial company wants to know if the about to be issued sub-prime mortgage will default.
In those situations we don’t have a value to predict directly as in a regular estimation. We’ll estimate the probability of something happening. P0 that it won’t happen, P1 that it will happen. P0+P1=1. That means that we’ll have a Bernoulli probability distribution with a mathematical expectation P1.
Imagining a two-dimensional situation, we’d have something like this:
Fitting two parallel lines with a diagonal line, that should be tough
That means that if we estimate with an ordinary least squares regression we’ll have a bad approximation for three reasons: the shape doesn’t resemble a line, the resulting line will span above 1 and below 0 (impossible probabilities) and R2 as a measure of goodness of fit will be higher the more separated the two dot clouds are.
The solution: using the logit model. We need something like this:
The function that we are trying to fit is the logit function, an special case of the logistics function. As you can see it asymptotically tends to one on the right side and to zero on the left side. That would mean that our regression would be now:
You need an statistical package to do that. You can even try to do it by means of a Gaussian distribution. That would be the probit model instead. Daniel McFadden earned the 2000 Nobel Prize in Economics partly because of his developments of econometrics with the logit regression.
Now, communications.
So, what’s the relationship with bits? In communications the basic unit of information is the bit. As you already know a bit just expresses a simple basic idea “0″ or “1″. That could mean “on” and “off”, but also “democrat” or “republican”, “male” or “female”. The simplest information, and, with a combination of them, more complex ideas: height, number of children, passport number, marital status.
When you’re sending bits, you’re making also a Bernoulli trial. You can either send zeros or ones. You don’t know if they’ll be ordered or not, but usually you imagine that they will have similar probabilities.
A measure of the “order” or “disorder” is the entropy. If there’s a similar quantity of zeros and ones, the entropy will be maximum, if they’re all ones, or zeros, minimum. There wouldn’t be any disorder if you only sent zeros. There would be no information either. So entropy must be kept to a maximum to send information. (And to ensure a working channel, that’s what randomisers are for).
There’s a function that measures the entropy of a Bernoulli trial:
The maximmum, of course, is when both probabilities are the same, when you are sending 0′s and 1′s with the same probability.
Now with coincidences
So where’s the funny thing? First let’s transform the logit regression function into a log function (take logarithms at both sides):
Now, let’s take the entropy of the Bernoulli trial and let’s derive it:
Do you see it? Here there is some coincidence going on. Both are the same function. (Well, there’s that minus sign, but who cares).
So, again, is Economy a Science?
Why do I care, you might ask. Well, lately I’ve been thinking about if Economy is solid enough as a Science or not. There’s a lot of things to say about that.
First I thought it wasn’t. What kind of science could have his rules changed by politicians? I posted my negative opinion here: Economy did not have solid enough foundations to say what was true or not.
But were the other sciences solid enough long ago? Maybe it’s just my perception of mine to think that Physics is more solid than Economics. Reality rules can’t be changed -for now-, but they can’t be totally determined either. Do you know about the Heisenberg uncertainty principle? It’s one of the greatest concepts that humanity has achieved. I have to blog about it some day.
There’s something deep going on here, laying the foundations of Economy as a science. The more I think about it, the more I can grasp or feel it. Even with planned communist economies, there still were cycles. Even when the Phillips curve did not work anymore, people still were making the same decisions, work more if there was more reward to it, hire cheaper if there was more workforce to choose from.
The more I think about it, the more I see Economy is a solid science in its own right.
Recent Comments