Sunday, February 18, 2007

Correlating nonsense

Play the Correlation Game
By: Jim Fedako
Ludwig von Mises: As a method of economic analysis econometrics is a childish play with figures that does not contribute anything to the elucidation of the problems of economic reality.[1]

Think that you might be capable of a crime? Worried that you're the next face to appear on the local most-wanted list? Wonder no more. Just take a gander at your high school senior photo and make an honest assessment of your appearance. If you were cute or handsome, no prison yard for you. If you were ugly, better call an attorney and bondsman right away ‘cause the slammer is less than eight years away.

Confused? Well, I'm only reciting research– or that which is called research – from the National Bureau of Economic Research. The abstract from Ugly Criminals, NBER Working Paper No. 12019, Issued in February 2006, includes the suggestive finding that, “the level of beauty in high school has an effect on criminal propensity 7-8 years later.” There you have it. Enough said. Crime is the result of looks, plain and simple. It gets worse; the labor market “provides an incentive” for ugly people to live lives of criminal activity. What an evil world we live in?

Compare this with what Mises.org has to offer: The Epistemological Problems of Economics; and, The Ultimate Foundation of Economics Science. Talk about a dismal science. Come on now, who really needs an Austrian Perspective on the History of Economic Thought? I mean, what’s the point? As my Dad likes to say, “What does it have to do with the price of tea in China?” Or, more importantly, what does all that have to do with one’s propensity to commit a crime?

Why read Mises, Rothbard, and others, when you can understand the world simply by downloading a couple of sets of specious federal data from the web, importing them into any statistical software package – go ahead and use MS Excel if you like -- and correlating these unrelated data points? If two thoughts cross your mind, correlate them. You can even call yourself a researcher and maybe convince the NBER to publish your findings. If your findings are provocative, or even if your title is provocative, you may find yourself sitting with national talking-heads on a cable news channel, not to mention having your name, photo and findings on the front page of the New York Times. In a moment, you are a star. Set the countdown clock at fifteen minutes and enjoy.

Of course there will always be that fear which occasionally enters your conscious mind; what if someone actually reads my study? The study’s title is certainly catchy but the underlying statistical findings are spurious at best. The abstract will suggest a lot about the research, but it’s really easy to suggest; learning and understanding are different matters since they take actual effort and knowledge. It appears that the more provocative the title, or suggestive the findings, the less initial review given to the actual study. (No correlative proof here, just an observation.) Later, after your clock has expired, another researcher will review your findings and publish his refutation and begin his fifteen minutes in the limelight.

Now if you want, you can get more sophisticated by first creating a model and then testing the model against your shallow pool of data. Of course models are best in the end since they add complexity and allow you to include intricate equations in your research paper; form over substance. Just for kicks, link the models and equations together in lines of esoteric jargon that is muddled at best. Muddled writing implies intellect, right? Not so says Rothbard. Muddled writing is usually the sign of muddled thinking. Muddled begets muddled.

Positivism, empiricism, et al, are predicated on the belief that only testable knowledge is valid. They like to claim that aprioristic knowledge is simply a game of semantics and word play; it’s all just tautologies. Really? Mises built his economics on a solid foundation; humans use means to obtain ends; they act. From this he created the science of economics that truly explains the processes of the market, whether free, hampered or socialistic.

From this foundation, Mises can state as a truth such concepts as inflation is the increasing on the supply of fiat money. Inflation is not a push/pull between consumers and suppliers. It’s not some monster that arises when you don't want it only to be settled down by the latest reading from Oracle of the Fed. Inflation is the printing of money or the loosening of credit. Simple. Doesn't matter what the latest researcher has shown using the latest statistical equations and programs. Inflation is what it is.

Reading Mises and Rothbard are sufficient to disprove an NBER study espousing how “investing” in some social program will reap societal benefits in future years. Whereas General Electric sends me my dividends on a regular basis, in all the years that politicians and governmental bureaucrats have invested my confiscated earnings on social programs, I have not received one dividend check. Not one penny. This despite the advertised billions and trillions of dividends due to me by now. Where’s my return on investment from the all pork used to fund NBER research? I don’t need a ten percent return, just three or four percent will suffice. Heck, I’ll even settle for one percent. Check’s in the mail I suppose.

See, as long as we are led to believe that the world can only be understood through empirical and statistical studies, we will never be able to question the true causes of our current malaise. Studies can only suggest. The truth can never be found in statistics, the noise level always drowns out any knowledge that could possibly be garnered.

So, why the continued funding for these studies? Ask yourself, “If ugly people are forced into lives of criminal activity due to the conditions of the current labor market, who or what could correct that market flaw?” If you were a good student in public schools, raise your hand and be prepared to respond, “My dear Uncle Sam is your man.” There you have it, the implicit and sometimes explicit solution to all the social ills noted by NBER research is always interventionism. Government needs to regulate the labor market and correct “the possibility that beauty may have an impact on human capital formation.” One or two more interventions and we can all cross the river to the Land of Cockaigne. At least that’s the picture they paint on the minds of children throughout the nation’s public school system. It’s even tough for adults – myself included -- to keep fighting the party slogans we heard for twelve years over the scratchy PA.

Read Mises, Rothbard, and others who sought liberty and prosperity for all of us. Spend some time digesting the insights found in The Epistemological Problems of Economics, The Ultimate Foundation of Economics Science, not to mention Human Action and Man, Economy, and State. And, disregard the drivel that is portrayed as science but is nothing less than a game of MS Excel.

By the way, the study that I am truly awaiting is the one that correlates PT Barnum’s fool with those willing to forego $5 in order to read the latest drivel from NBER. That’s a study I'll purchase. No, wait. Wouldn't that make me the fool and PT correct once more?


1. The full quote from, Ludwig von Mises, The Ultimate Foundation of Economic Science, 1978. "Deluded by the idea that the sciences of human action must ape the technique of the natural sciences, hosts of authors are intent upon a quantification of economics. They think that economics ought to imitate chemistry, which progressed from a qualitative to a quantitative state.[1] Their motto is the positivistic maxim: Science is measurement. Supported by rich funds, they are busy reprinting and rearranging statistical data provided by governments, by trade associations, and by corporations and other enterprises. They try to compute the arithmetical relations among various of these data and thus to determine what they call, by analogy with the natural sciences, correlations and functions. They fail to realize that in the field of human action statistics is always history and that the alleged "correlations" and "functions" do not describe anything else than what happened at a definite instant of time in a definite geographical area as the outcome of the actions of a definite number of people.[2] As a method of economic analysis econometrics is a childish play with figures that does not contribute anything to the elucidation of the problems of economic reality."

No comments: