Some thoughts on forecasting

Shashank Patil, a BSc student writes in with this query:

“Could you suggest books(those criminally thick ones work well too!) or any other reference to understand the nuances of forecasting better? (particularly how to be skeptical about specific models, their shortcomings or what thought process should follow whenever I see a forecast model and its predictions, etc.)
I guess a lot of this should come with experience rather than through purposeful effort. But any guidance on this should be of great help.”

First things first: I wish I had had the wisdom to ask this question at that age. I and a friend of mine were just discovering the joys of playing around with Microsoft Excel and MATLAB, and were more focused on learning how to code and model than on asking “Well, hang on. Does this even make sense?” Kudos, Shashank, for being sceptical. It’ll serve you well while learning econometrics!

Now, that being said, I’ll get to books and resources a little further below, but first some thoughts about forecasting that might help.

There are, to my mind, three ways to forecast something.

The first is to build a model in which the outcome is a function of measurable inputs, excluding time. What that means in non-academic gobbledygook is this:

 

That’s a model, with measurable inputs. If x, then y, and if y, then z. And you can keep this going for as long as you want. You can guess, with some allowances for error, what’ll happen at the end. Raise interest rates, and people will borrow less. If people will borrow less, people will spend less. If people will spend less, demand will go down. And on and on and on.

Economic models are more complicated, because they deal with us, human beings. And much as we economists would like human beings to be rational, we don’t always live up to our expectations. But that apart, this is one way to forecast. Build a model, which is basically a scaled down version of reality, and hope that the model can “predict” what’ll happen next.

Or, and this is where we enter the badlands of econometrics, we can do time series modeling. Time series modeling is special in the sense that we try and predict what happens next on the basis of what has gone before.

 

 

Times series chart example from Russia
Click here for original chart and article

What will the value be in April 2000? A time series model will try and “guess” the value, based on past trends and values. The reason I tend to be a little (well, ok, more than a little) sceptical of this kind of analysis is because a) we ignore everything else that is going on in the world and b) absence of evidence is not evidence of absence.

That is to say, just because it has not happened in the past is no reason to believe that it will not happen in the future. But time series models, by definition, project out into the future by looking at the past!

And finally, betting markets! Crowdsource what the future will look like, by asking people to bet on their view of what the future will be like.

 

Here’s the introduction from a Wikipedia article (but do read the whole thing)

“Prediction markets (also known as betting markets, political betting markets, predictive markets, information markets, decision markets, idea futures, event derivatives, or virtual markets) are exchange-traded markets created for the purpose of trading the outcome of events. The market prices can indicate what the crowd thinks the probability of the event is. A prediction market contract trades between 0 and 100%. It is a binary option that will expire at the price of 0 or 100%. Prediction markets can be thought of as belonging to the more general concept of crowdsourcing which is specially designed to aggregate information on particular topics of interest. The main purposes of prediction markets are eliciting aggregating beliefs over an unknown future outcome. Traders with different beliefs trade on contracts whose payoffs are related to the unknown future outcome and the market prices of the contracts are considered as the aggregated belief.”

Also read Bryan Caplan on betting. And Robin Hanson. And Vitalik Buterin.

Now all that being said, here are the books I would recommend you read:

  1. Walter Enders: Applied Econometric Time Series. A little advanced, perhaps, but it remains, for me, the bible of time series forecasting.
  2. A Little Book of R for Time Series Forecasting. Short lovely read, with lots of examples you can try for yourself in R.
  3. Superforecasting (somewhat tangential, but a great read)
  4. Mastering Econometrics, an online video series, by Joshua Angrist (who also has a lovely book called Mostly Harmless Econometrics).

Thank you for the question, Shashank!

Links for 13th May, 2019

  1. “There should be limits, too, on the rights investors can sign away. In recent years, some companies — such as Smartsheet and Twilio — have done dual-class issues in which the extra voting rights expire after a certain number of years. These sunset provisions preserve the potential benefits of leaving initial control in the hands of founders, while avoiding the risk of creating a dynastic birthright. That’s a sensible compromise. The Securities and Exchange Commission, or the exchanges it oversees, should make such provisions mandatory.”
    ..
    ..
    A very useful article to help understand how to think about IPO’s, Uber, Lyft valuations, mandatory disclosures from firms and how they try to get around the issue – and the excerpt above is yet another example of a favorite adage of mine: the truth always lies in the middle.
    ..
    ..
  2. “We find that between 1300 and 1400 a 10 percentage point higher Black Death mortality rate was associated with a 8.7 percentage point fall in city population, but between 100 and 200 years later, the impact of mortality was close to zero. When we examine the spillover and general equilibrium effects of the Black Death on city populations, we similarly find negative effects in the short run, and no effects in the long run. Cities and urban systems, on average, had recovered to their pre-Plague population levels by the 16th century.”
    ..
    ..
    A worrying article, especially towards the end, but two major takeaways for me: cities matter, and trade matters. But my major takeaway is there is (yet more) cause for worry.
    ..
    ..
  3. “Unfortunately, the world’s most prominent specialists are rarely held accountable for their predictions, so we continue to rely on them even when their track records make clear that we should not. One study compiled a decade of annual dollar-to-euro exchange-rate predictions made by 22 international banks: Barclays, Citigroup, JPMorgan Chase, and others. Each year, every bank predicted the end-of-year exchange rate. The banks missed every single change of direction in the exchange rate. In six of the 10 years, the true exchange rate fell outside the entire range of all 22 bank forecasts.”
    ..
    ..
    Forecasts are useless. I cannot be more serious when I say this. Forecasts are useless. But foxes are better at the impossible then the hedgehogs – this article helps you understand these terms, and their usefulness. This blog is about becoming a better fox!
    ..
    ..
  4. “Again, one can argue that the amount of redistribution should be larger. But it would be untrue to argue that a significant amount of redistribution–like doubling the after-taxes-and-transfers share of the lowest quintile–doesn’t already happen. ”
    ..
    ..
    The always informative Timothy Taylor on taxes, their composition, their effectiveness and the resulting redistribution in the United States of America. Also, read the book that is reviewed in this article – the entire book is worth your time, but the chapter on income tax is what I was reminded of.
    ..
    ..
  5. “When Paul Romer expresses an opinion, it is always worthwhile to listen because it is always well-considered. In an opinion piece in the New York Times, he puts forward a proposal to restore what he terms is the “public commons” of the provision of information in support of democracy. He actually puts forward two linked proposals: one for a target on targeted ads by digital platform companies and a proposal that the tax is progressive (which may be a check on dominance). The latter is interesting but I will just focus on the former here.”
    ..
    ..
    I do not recollect if I linked to the Paul Romer piece that is linked to in the excerpt above – in case I did not, please go ahead and read it. The rest of the current article speaks about why Romer’s proposal is a good idea, but not necessarily implementable right away.

Links for 24th April, 2019

  1. “Really? When is the last time you ran a search with DuckDuckGo? Too often, he seems to be stretching the evidence. He argues that, given the social aspects of the workplace, “companies are actually responsible for some of our most important relationships.” But that’s a function of work — not of corporate life. People at nonprofits make friends, too. Cowen asserts in defense of Amazon, “My options as a book consumer never have been better.” He includes as evidence of a competitive book market the option (which he doesn’t condone) of “illegal downloads of free PDFs.” Jeff Bezos must rue such defenders. (Bezos founded Amazon and owns The Washington Post.)”
    ..
    ..
    Roger Lowenstein reviews Tyler Cowen’s latest book. I myself have not read it yet, but the review was interesting to me, in particular this excerpt about illegal PDF’s and how they encourage competition.
    ..
    ..
  2. “Alwyn’s related analysis of published studies is even more striking. He shows that, in a sample of 1359 IV regressions in 31 papers published in the journals of the American Economic Association,
    “… statistically significant IV results generally depend upon only one or two observations or clusters, excluded instruments often appear to be irrelevant, there is little statistical evidence that OLS is actually substantively biased, and IV confidence intervals almost always include OLS point estimates.” ”
    ..
    ..
    Econometric nerds/students only (consider yourself warned) – but IV isn’t as great as it is made out to be. Occam’s razor is massively ignored in econometrics.
    ..
    ..
  3. “The Fiscal Affairs Department and the Institute for Capacity Development of the IMF are pleased to announce that the online course on Public Financial Management (PFM) will relaunch on May 1, 2019 and remain open year-round. In its two previous offerings, this free online course has been taken by more than 2,200 participants in 194 countries, with very high satisfaction rates. Taught by more than 15 experts of the Fiscal Affairs Department, the course is open for government officials, staff of bilateral and multilateral development agencies, civil society organizations, parliamentarians, academics and the general public. The course has been updated in 2019 to reflect the revisions brought to IMF’s PFM standards and tools and adopted in the last twelve months – namely the Public Investment Management Assessment (PIMA) framework and the Natural Resource Management pillar of the Fiscal Transparency Code (FTC).”
    ..
    ..
    You might, as a student of economics or policy making, want to consider taking this course.
    ..
    ..
  4. “So why, then, does the government tax, under the MMT view? Two big reasons: One, taxation gets people in the country to use the government-issued currency. Because they have to pay income taxes in dollars, Americans have a reason to earn dollars, spend dollars, and otherwise use dollars as opposed to, say, bitcoins or euros. Second, taxes are one tool governments can use to control inflation. They take money out of the economy, which keeps people from bidding up prices.And why does the government issue bonds? According to MMT, government-issued bonds aren’t strictly necessary. The US government could, instead of issuing $1 in Treasury bonds for every $1 in deficit spending, just create the money directly without issuing bonds.”
    ..
    ..
    Yet another explainer of MMT – it’s counterintuitive (at least to me), and I’m still not sure it makes sense and will work – but I understand it better than I did before upon reading this article.
    ..
    ..
  5. “This is an issue for economics too: the construction of the deflators used to turn nominal pound or dollar GDP into ‘real’ GDP, on which so much policy hangs, relies on a theory of constant, known preferences which determine the utility of consumption, and yet modern economic growth is all about creating wants for new goods and services for which preferences have to be created. So at a time of rapid innovation it is not at all clear what the deflators and ‘real’ GDP measures are measuring.”
    ..
    ..
    Diane Coyle reviews a book that helps us understand Amartya Sen’s work better. I found this excerpt above quite interesting.