Model Failure: Unreliable Statistical Index (LEI)

More testament of the glaring failures of statistical aggregates or econometrics from Dr. Ed Yardeni, (bold emphasis mine)

I’m not a big fan of leading economic indexes (LEIs). They can be quite misleading. They are constructed by well-intentioned economists with the intention of providing an early warning that a recession is coming in a few months or assurance that the economy is likely to expand in coming months. These man-made indexes combine a bunch of indicators that purportedly lead the business cycle. When they fail to do so, the men and women who made these indexes recall them, retool them, and send them back out for all of us to marvel at how well these new improved versions would have worked in the past. I can accurately predict that when they fail in the future, they will be recalled and redesigned yet again.

This just happened to the US LEI. The Conference Board has made the first major overhaul of the components of the LEI since it assumed responsibility of the index in 1996. It replaced real money supply with its proprietary leading credit index, and the ISM supplier delivery index with the new orders index. In place of the Thomson Reuters/University of Michigan consumer expectations measure, it will now use an equally weighted average of its own consumer expectations index and the current measure. Also, the nondefense capital goods gauge was tweaked to exclude commercial aircraft.

The impact of these changes has been shocking, and really questions the credibility of constructing LEIs.

As shown above, econometricians and statisticians laboriously attempt to fit evidence into models in the hope that calibrating them would increase their predictive capabilities. Unfortunately, they don’t. That’s because social sciences isn’t physics.

As the great Friedrich von Hayek wrote,

the sort of knowledge with which I have been concerned is knowledge of the kind which by its nature cannot enter into statistics and therefore cannot be conveyed to any central authority in statistical form. The statistics which such a central authority would have to use would have to be arrived at precisely by abstracting from minor differences between the things, by lumping together, as resources of one kind, items which differ as regards location, quality, and other particulars, in a way which may be very significant for the specific decision. It follows from this that central planning based on statistical information by its nature cannot take direct account of these circumstances of time and place and that the central planner will have to find some way or other in which the decisions depending on them can be left to the "man on the spot."