Forecasting? Wall Street is Wising Up

Wall Street Wises Up to the Folly of Forecasting
One economist says what should be obvious: Making predictions only means you will be either wrong or lucky.
Bloomberg, December 15, 2017




It is that time of year, when the financial industry engages in its annual ritual of making forecasts, which is usually little more than the prelude to looking foolish. Titles like “Outlook for 2018, “What to expect in the new year,” or some variation thereof litter the landscape. Over the years, it has been my distinct privilege (and truth be told, pleasure) to point out how silly this process is.

On this topic, I am thrilled to welcome some new company. Some of the bigger firms and mainstream economists have recognized that this sort of game is no longer worth the effort. Perhaps no one is better placed to recognize the absurdity of the annual forecasting binge than UBS global chief economist, Paul Donovan. In a note to clients this week, he exhorts his economic brethren to stop the ridiculous prognostications, and instead, provide meaningful value to clients. In a note titled “What can we forecast about next year?,” Donovan bluntly states:

Economists should not make forecasts.

December always has a rash of economic forecasts for the year ahead. The reception areas at CNBC and Bloomberg TV are crowded with mobs of economists fighting to get their forecasts on air. But there are big problems with making precise economic forecasts.

Economic models are not precise. Models use lots of assumptions. Those assumptions may not turn out to be true. Models give a range of possibilities rather than a single, certain number. Economists know and understand these issues. However, the world of hashtag economics does not allow for all of this to be explained. It is difficult to warn about possibility ranges and underlying assumptions in 280 characters. This is why economists should not use Twitter (follow me @PDonovan_Econ). Economic views often give a false sense of precision, because the reporting of economics is simplified and shortened. That precision simply is not there, in our view.

There is a lot of wisdom in those three paragraphs; let’s unpack them to see if we can identify what there is to learn.

 1) The problem with models. I have over the years cited British statistician George Box’s famous statement that “Essentially, all models are wrong but some are useful.” What Donovan is referring to is a variant on this idea — models lack precision, and are built upon assumptions. If we recognize their inherent limitations, however, they might be useful.Models create an imperfect depiction of whatever universe you are trying to simulate on a spreadsheet or a computer. It could be the stock market, the broader economy, climate change, whatever. Econometric models such as those Donovan referred to let us play with a variety of different scenarios, changing different inputs to learn what that does to possible outcomes. By understanding the limitations of this process, we can generate a better understanding of potential futures. But it is crucial for economists to not forget the limitations of these models: they must closely examine their assumptions; they need to consider the probabilistic range of what could happen; they cannot ignore variability and randomness in future outcomes.

2) Forecasting is marketing: Noting the mad crush at TV networks — “mobs of economists fighting to get their forecasts on air” — is an acknowledgement of this point. The state of the art of economic forecasting is pretty lousy; pretending otherwise is nothing more than a sales pitch.

We have noted this repeatedly; it is encouraging to see UBS picking up on this concept.

3) Precision is misleading. The tendency of economists to make economic forecasts with any sort of precision is an enormous error. Donovan cleverly addresses this, writing: “We believe investors just need to know that the world is doing OK. Inflation may rise a little. Central banks will likely slowly tighten policy. Economics is exciting enough; there is no need to get dramatic about decimal points.”

That sort of ambiguous, soft forecast is a much more realistic approach than the specific nonsense so often used by economists. No one put this any better than 19th century novelist William Gilmore Simms, who observed “I believe that economists put decimal points in their forecasts to show they have a sense of humor.”

As we pointed out last month, people are not especially good at forecasting. Many economists seem to be susceptible to cognitive errors and biases. It is encouraging to see at least one practitioner of the dismal science acknowledge this so publicly.



Originally: Wall Street Wises Up to the Folly of Forecasting


Posted Under