Home > Uncategorized > Econometrics — analysis with incredible​ certitude​

Econometrics — analysis with incredible​ certitude​

from Lars Syll

9780199679348There have been over four decades of econometric research on business cycles …

But the significance of the formalization becomes more difficult to identify when it is assessed from the applied perspective …

The wide conviction of the superiority of the methods of the science has converted the econometric community largely to a group of fundamentalist guards of mathematical rigour … So much so that the relevance of the research to business cycles is reduced to empirical illustrations. To that extent, probabilistic formalisation has trapped econometric business cycle research in the pursuit of means at the expense of ends.

The limits of econometric forecasting have, as noted by Qin, been critically pointed out many times before. Trygve Haavelmo assessed the role of econometrics — in an article from 1958 — and although mainly positive of the “repair work” and “clearing-up work” done, Haavelmo also found some grounds for despair: 

Haavelmo-intro-2-125397_630x210There is the possibility that the more stringent methods we have been striving to develop have actually opened our eyes to recognize a plain fact: viz., that the “laws” of economics are not very accurate in the sense of a close fit, and that we have been living in a dream-world of large but somewhat superficial or spurious correlations.

Maintaining that economics is a science in the ‘true knowledge’ business, I remain a sceptic of the pretences and aspirations of econometrics. The marginal return on its ever higher technical sophistication in no way makes up for the lack of serious under-labouring of its deeper philosophical and methodological foundations that already Keynes complained about. The rather one-sided emphasis of usefulness and its concomitant instrumentalist justification cannot hide that the legions of probabilistic econometricians who give supportive evidence for their considering it ‘fruitful to believe’ in the possibility of treating unique economic data as the observable results of random drawings from an imaginary sampling of an imaginary population, are skating on thin ice.

A rigorous application of econometric methods in economics really presupposes that the phenomena of our real world economies are ruled by stable causal relations between variables. The endemic lack of predictive success of the econometric project indicates that this hope of finding fixed parameters is an incredible hope for which there, really, is no other ground than hope itself.

  1. deshoebox
    December 14, 2018 at 9:54 pm

    I respectfully disagree. I don’t think economics as currently taught and practiced is any kind of science. It starts with false premises (almost always hidden and unacknowledged) and it uses bad reasoning to build on this shaky foundation. Part of the purpose of economics is to inform good public policy decision making. If it can’t do that and can’t even predict major economic events, it can’t really be regarded as useful. And it certainly can’t call itself a science.

  2. December 15, 2018 at 12:14 am

    A simple multiple regression with total private debt, the first derivative of private debt(credit), and the second derivative of private debt(credit impulse), is well over R squared of 93% over at least the past three decades. This is large but not spurious. By far the largest contribution is that of credit.

  3. December 15, 2018 at 4:23 pm

    “The endemic lack of predictive success of the econometric project indicates that this hope of finding fixed parameters is an incredible hope for which there, really, is no other ground than hope itself.”

    This quote actually describes most economics and not just econometrics. The article argues that econometrics and shown the standard economics models don’t add up and the standard economic models lack predictive success. IMO

    But on the subject of “hope”, I have a new specialized area of economics that offers a strong hope for solving poverty and making a profit at the same time in a free market. Visit the hOEP project (hOurs Equals Price) , https://sites.google.com/view/the-hoep-project , if you’re interested in a way for sellers to make more profit by giving larger, more frequent and more convenient low income price discounts. Economics are used in the project research to show how sellers can make a profit by reducing financial inequality. If you know econometrics then tell me how you could apply it to the project please.

  4. Norman L. Roth
    December 15, 2018 at 10:26 pm

    “Peter Blogdonovich” {???},

    May I humbly suggest that you have just uttered a tautology. Hardly a rarity anywhere. But you have inadvertently chosen statistical “newspeak” as a mode of expression.Please consult George Orwell’s 1984. Try thinking about it a bit.

    GOOGLE: {1}Norman L. Roth {2} Norman L. Roth, Technological Time {3} Norman L. Roth, Economics of Work. I also suggest you introduce yourself to a subject called ‘Epistemology’ .

    It could prove very practical in your case .Also, Lars Syll is quite well versed in that subject as well as in the limits of Statistical methodology, and the temptations to fallacy contained therein. May I also suggest that you try John Maynard Keynes; A TREATISE on PROBABILITY,1921. Not to mention Frank Knight’s contribution written about the same time.

    • Craig
      December 16, 2018 at 4:53 pm

      Tautologies are a hint, as knowledge can only be perceived by a knower….no matter to whom or to what one attributes such.

      Also, telos and technos being another duality to derive an aspect of the natural philosophical concept and/or experience of grace/consciousness, in this case process, you should be affirming what I post here.

      “…..why do you kick against the goads?”

    • December 16, 2018 at 5:13 pm

      The regression is for unemployment. My bad. According to Richard Vague, Total private debt and its derivatives does a bang up job predicting financial crisis over the trailing few centuries.
      http://www.upenn.edu/pennpress/book/15313.html
      My point was, Paul Krugman still teaches Loanable Funds, the predicate assumption of which is that private debt does not affect any important macroeconomic outputs. This despite the fact that total private debt and its derivatives account for something like 98% of the variance in unemployment plus simple trigger criteria based on total private debt predicts financial crisis reliably. The claim that no model reliably produces a high correlation that is not spurious is false. Macroeconomics simply made one wrong turn; ignoring private debt per loanable funds.
      Steve Keen and Michael Hudson are leading the way on this too. I’m glad to learn someone is bothering to read my posts here. I was starting to wonder. Thank you.

      • Craig
        December 16, 2018 at 7:23 pm

        Yes, their insights (Keen’s and Hudson’s) are valid re-discoveries of the fact that modern technologically advanced economies are INHERENTLY cost inflationary primarily due to the ever increasing depreciation costs of its technology, its own fixed capital and the removal of money from one cycle of production to another via re-investment or retained earnings.

        Douglas and his followers made the mistake of falling into the spell of DSGE by only trying to “fill the gap” instead of inverting individual monetary scarcity into abundance with the paradigm changing policies of Wisdomics-Gracenomics. Keen wants
        a one-off “modern debt jubilee” which also still has the stench of DSGE hanging around it despite his vehement critique of it, and Hudson’s financial parasitism correctly identifies which paradigm must be changed but doesn’t have a comprehensive policy plan to accomplish it. Finally, they’re all so addicted to abstraction that they seemingly can’t come into present time to spot the triple power point for policy of retail sale.

  5. December 16, 2018 at 5:47 pm

    By the way, what we’re talking about here is the Bayesian pretest probability, specifically; getting that right. Very important.

    https://www.bmj.com/content/363/bmj.k5094

    Quite hilarious IMO and on point.

  6. December 25, 2018 at 1:25 pm

    In my work I’m often inundated by testimony, reports, graphics, and econometrics by witnesses to “show” that whatever case they argue is sound and proven. In testimony I always make the same simple point in response. I ask the witnesses to “explain as simply as possible” how the graphics, reports, etc. they offer prove what they claim. My position is that graphics, equations, and econometrics are only lines on paper till it is explained how and why they make a proof and why they cannot be challenged. I’ve won this argument about 400 times.

  1. No trackbacks yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: