Steve Kass

A lot of people are racking their brains trying to explain some wrong numbers that two Harvard School of Public Health researchers graphed. The real explanation of the surprising result is that the authors got their crosstabs backwards. They were looking for these numbers (the ones circled in green), which show the percentage of self-identified strong Democrats who say they are in poor health (9.1%), and the percentage of self-identified strong Republicans say they are in poor health (5.0%).

Unfortunately, they graphed these numbers (the ones circled in red) which represent something else:

Among many other places, the wrong results (which contained several other wrong numbers caused by the same mistake) were reported here, here, and here, except that it was reported as surprising research, not wrong research. These reports have generated lively discussions about why Democrats are in such poor health. Except they aren’t. With luck, many of the people reading about this will eventually find the answer here.

In today’s New York Times, Warren Buffett tells us to buy stocks now, while people are scared and times are tough. Wait for the robins, he says, and spring will be over.

He offers a historical illustration to support his advice:

During the Depression, the Dow hit its low, 41, on July 8, 1932. Economic conditions, though, kept deteriorating until Franklin D. Roosevelt took office in March 1933. By that time, the market had already advanced 30 percent. Or think back to the early days of World War II, when things were going badly for the United States in Europe and the Pacific. The market hit bottom in April 1942, well before Allied fortunes turned. Again, in the early 1980s, the time to buy stocks was when inflation raged and the economy was in the tank. In short, bad news is an investor’s best friend. It lets you buy a slice of America’s future at a marked-down price.

No doubt buying on July 8, 1932 would have been opportune. The Dow had fallen for nearly three years, dropping almost 90% off its high of 380 in September, 1929. Today, the Dow has been falling for only a year and is down 40% from its 2007 high. Coincidentally, that’s just the Dow’s position a year after the September 1929 high. Down 40% in the first year. If now is the time to buy, was the historical parallel of now, September, 1930, the time to buy? Not at all. The Dow would go on to lose another 80% in the 22 months after September 1930, not recovering for another 18 years. Not until 1950 would stocks bought in 1930 begin to show a profit.

Buy low, sell high. That’s great advice - for time travelers. Regular folk don’t know whether we’re at the bottom or whether the bottom is far away. Buffett understands the market better than I do, and his recommendation may be sound. But his historical excerpt doesn’t support buying now. Not that any historical excerpt can support any recommendation in the crazy game of chance we call the stock market.

From the Wall Street Journal’s “Washington Wire” today (notes added):

The two presidential campaigns have issued competing timelines of events today leading up to McCain’s call to cancel the debates. Here is Obama’s version:

“At 8:30 this morning, Senator Obama called Senator McCain to ask him if he would join in issuing a joint statement outlining their shared principles and conditions for the Treasury proposal and urging Congress and the White House to act in a bipartisan manner to pass such a proposal. At 2:30 this afternoon, Senator McCain returned Senator Obama’s call and agreed to join him in issuing such a statement. The two campaigns are currently working together on the details.”

Shortly after, the McCain campaign released their version:

“Senator Obama phoned Senator McCain at 8:30 am this morning but did not reach him. The topic of Senator Obama’s call to Senator McCain was never discussed [1]. Senator McCain was meeting with economic advisers and talking to leaders in Congress throughout the day prior to calling [2] Senator Obama. At 2:30 pm, Senator McCain phoned Senator Obama and expressed deep concern that the plan on the table would not pass as it currently stands. He asked Senator Obama to join him in returning to Washington to lead a bipartisan effort [4] to solve this problem.”

Translator’s notes:

[1]: “Never discussed”: If Obama did not reach McCain, nothing was discussed. Note that the following is equally true, though understandably the McCain camp chose not to include it in their press release: “A McCain plan to withdraw from the race and apologize for his repeated lies was not discussed.”
[2]: “prior to calling”: Before 2:30, but in all likelihood, not at 8:30, when Obama phoned with the joint statement idea, or the McCain statement would have been specific. Had the McCain camp been cleverer, they wouldn’t have mentioned the exact time of the call at all, because the single mention draws attention to the later non-mention.
[3]: “lead a bipartisan effort”: Here is the McCain camp’s best use of rhetoric in the release. (”Best”, of course, is relative, and does not imply lack of sleaze.) They have rhetorically taken Obama’s good idea (”issuing a joint statement”), kept the concept (”<verb> joint <good thing>”), and concocted a replacement readers might believe is theirs (”lead a bipartisan effort”). The indefinite article “a” emphasizes that there was no earlier mention of a bipartisan effort, and it may be true there wasn’t. But McCain surely knew at this point that Obama had suggested a joint statement, and I bet they talked about it. 

So this is the likely sequence of events:

• Obama called McCain at 8:30 am.
• McCain hears the phone ring, sees it’s Obama, and lets the call go to voice mail. There’s no conversation.
• McCain listens to the voice mail and knows that Obama came up with a good idea before him (McCain).
• Later on, McCain has a few meetings and phone calls.
• At 2:30pm, McCain called Obama, who answered.
• McCain and Obama discuss doing something together.
• Obama’s camp issues a press release about all this.
• McCain’s camp reads the Obama press release. They immediately realize how damaging it would be to ignore, since it hits them hard: Obama had a good idea, and first; McCain didn’t answer an 8:30 call, so where was he?; and regarding any bipartisanship between the candidates, Obama is in control and decisive.
• The McCain team scrambles its writers, and “shortly” afterwards, they issue their own press release crafted to address the strong points of the Obama release as fast as they can. They choose not to lie outright. (You can get in trouble when you make up lies in a hurry.)

The Journal, which is no way “in the tank” for Obama, is appropriately cynical.

With Software, Till Tampering Is Hard to Find
By Roy Furchgott
August 29, 2008
http://www.nytimes.com/2008/08/30/technology/30zapper.html

As hard as zapper software is to detect, it is easy to make, said Jeff Moss, organizer of the annual hacker convention Def Con. “If it runs on a Windows system and you are a competent Windows administrator, you can do it,” he said.

According to analysts at the consulting firm Frost & Sullivan, 85 percent of all point-of-sale systems, as cash registers are called, run on the Windows operating system, although other systems are also vulnerable.

Don’t blame the operating system; blame the hardware. Modern technology has replaced paper and indelible pen (a twentieth-century write-once, read-only data collection and storage system with physical properties that make forgery difficult; see http://www.flickr.com/photos/stevegarfield/616793140/) with the technological equivalent of a Magic Slate (a 1970’s toy; see http://www.landofthelost.com/slate.htm), which is child’s play to alter.

Do electronic systems that record transactions on write-once storage even exist? The technology exists, and it’s dirt cheap. Why can’t businesses be required to keep permanent, inalterable transaction records? Ultimately it may be impossible to prevent a crooked business owner from embezzling from his or her own business or committing tax fraud. But why make life easy for them by allowing Magic Slates for accountability?

DNSstuff.com follows a time-honored sleazy marketing model. They’ll run a free test of your domain and tell you you’ve got problems, but they won’t give you the details unless you sign up for a free trial of their $79/year tools. Their free test even reports critical errors on their own site. What’s the old line about cheating your own mother?

From “A Glut of One-Bedroom Apartments” in today’s New York Times:

Brokers say that many people who bought their apartments at or near the top of the market and now must sell are often simply trying to avoid losing money on the deal.

In May 2007, John and Wendy Penn bought a one-bedroom on West 72nd Street for $650,000. The couple, whose main residence is on Long Island, wanted an office and a pied-à-terre in Manhattan to expand their insurance business.

They bought the apartment as a long-term investment and quickly completed about $30,000 in renovations, including the restoration of the apartment’s prewar details. But when Mr. Penn became an independent insurance agent, he no longer needed space in Manhattan.

So in February, the couple put the apartment up for sale, pricing it at $769,000. Three price cuts later, the apartment is listed at $725,000 and still has not sold.

It doesn’t sound like the Penns are “simply trying to avoid losing money.” They tried to sell their apartment nine months after they bought it for $119,000 more than they paid. Now they’re only asking $75,000 more, which should cover their renovations, the sales agent’s commission, and the property taxes they paid. Does the Times think a pied-à-terre in Manhattan (or any housing anywhere) is supposed to be free?

Under the headline “Rise in TB Is Linked to Loans From I.M.F.”, Nicholas Bakalar writes for the New York Times today that “The rapid rise in tuberculosis cases in Eastern Europe and the former Soviet Union is strongly associated with the receipt of loans from the International Monetary Fund, a new study has found.”

The study, led by Cambridge University researcher David Stuckler, was published in PLoS Medicine and is online at (URL may wrap):

http://medicine.plosjournals.org/perlserv/?request=get-document&doi=10.1371/journal.pmed.0050143&ct=1.

Cambridge, Schmambridge. First clue: the Times quotes Stuckler: “When you have one correlation, you raise an eyebrow,” Mr. Stuckler said. “But when you have more than 20 correlations pointing in the same direction, you start building a strong case for causality.”

In twenty post-communist countries, the variable “participated in an IMF loan program in year Y” was significantly negatively associated with “TB rate per 100000 people,” whether using rate of cases, of deaths, or of new cases.

After reading the paper and looking at much of the source data, I agree with William Murray, an IMF spokesman also quoted in the article: “This is just phony science.”

Why do I agree with Murray?

Take the supporting table below, for example. It shows all the TB mortality data from “did not participate in an IMF loan program” years: year-to-year percentage changes in TB mortality rates (based on Logs) [sic]. Among the 45 values are 31 0.00s and nothing else close to zero. Almost half the nonzero values are from Poland and Hungary, but—oddly—the change is nonzero in odd-numbered years and zero in even-numbered years. There are four -22.31s, two -18.23s, a 15.42 and a -15.42, a 13.35 and a -13.35, and four stray values, one of which is -69.31. Now I know -0.6931 from calculus (the natural log of ½), and I googled 0.2231: it’s the natural log of 0.8. (There were about four times as many “did participate” country-years, for a total of 200+ data points.)

If you haven’t guessed, the data here, which mostly express stable or declining TB mortality, and which found the entire study, and which the authors attribute significantly to non-participation in IMF loan programs, are 4-significant-digit percentage changes between logs of adjacent very small positive integers. The small integers are from the Global Tuberculosis Database, queryable here: http://www.who.int/globalatlas/dataQuery/default.asp. This WHO data is rounded to whole numbers and for the countries and years studied, ranged between 1 and 20.

While this data is crude, I don’t doubt the study’s main finding: among post-communist countries, “participated in an IMF loan program in year Y” was significantly negatively associated with “TB rate per 100000 people.” What I doubt is that the relationship has anything to do with the IMF loan program.

The timeframe studied was 1989 to 2003, and a quick look at the data reveals a pattern to which are the “in an IMF loan program” years for the countries studied. Most countries began participating in 1991, 1992, or 1993, and most countries continued their participation through 2003, the end of the study timeframe. During this time, TB was on the rise, and there’s no question the mid nineties were not a typical period.

While the authors mention many correction strategies and tests to avoid one or another kind of bias, they didn’t mention the way in which “in program” years were distributed as one potential confounder. I can’t see how they ruled it out. There data isn’t there. From 1994 to 1997, there are only 10 “not participating” data points, mostly from Czech Republic, Slovenia, and Poland, which countries were anomolous in having shown no increase in TB during their IMF years. Some countries, Bosnia for example, seem to have been omitted from this part of the analysis, despite having participated in an IMF loan program and data being available from WHO.

The countries studied included Russia, with 140,000,000 people, as well as Estonia, Latvia, Macedonia, Slovenia, Albania, Armenia, Bosnia, Lithuania, counted together having less than 20% of Russia’s population. The authors acknowledge the possibility of ecological fallacy with little investigation. Summary statistics, such as the mean and standard deviation of TB rate among the countries, are unweighted by population, and fail to reflect the real situation. Over one time period quoted, the number resulting from taking the average of each countries TB rate, unweighted for population, went up 30%, but the TB rate among the population under study in fact doubled. Whether this changes any interpretation, I can’t say, but it does make a difference.

Not only am I not a statistician, I’m not an economist, and I have no idea whether the IMF did great things or not in mid-nineties eastern europe and former Soviet Union. But Stuckler and colleagues haven’t convinced me of anything.

http://finance.yahoo.com/q?s=VMMXX:

Strange. The HTML source for this page shows a yield of 2.39%, not 92,318.20%. In both IE7 and Firefox, 2.39% shows up as the yield when the page is first rendered, but changes immediately to 92,318.20%. The yield is getting its significant digits from the Assets value, but why is a mystery to me.

A Reuters News Service article today reports [emphasis mine] “If both your parents have Alzheimer’s disease, you probably are more much likely than other people to get it, researchers said on Monday.” What if they both have dyslexia?