Home > Uncategorized > Top 10 critiques of econometrics

Top 10 critiques of econometrics

from Lars Syll

top-10-retail-news-thumb-610xauto-79997-600x240

•Achen, Christopher (1982). Interpreting and using regression. SAGE

•Berk, Richard (2004). Regression Analysis: A Constructive Critique. SAGE

•Freedman, David (1991). ‘Statistical Models and Shoe Leather’. Sociological Methodology

•Kennedy, Peter (2002).  ‘Sinning in the Basement: What are the Rules? The Ten Commandments of Applied Econometrics’. Journal of Economic Surveys

•Keynes, John Maynard (1939). ‘Professor Tinbergen’s method’. Economic Journal

•Klees, Steven (2016). ‘Inferences from regression analysis: are they valid?’ Real-World Economics Review

•Lawson, Tony (1989). ‘Realism and instrumentalism in the development of econometrics’. Oxford Economic Papers

•Leamer, Edward (1983). ‘Let’s take the con out of econometrics’. American Economic Review

•Lieberson, Stanley (1987). Making it count: the improvement of social research and theory. University of California Press

•Zaman, Asad (2012). ‘Methodological Mistakes and Econometric Consequences’. International Econometric Review

  1. dmf
  2. Paul Davidson
    November 20, 2016 at 6:29 pm

    you apparently avoid indicating the most important reason why macroeconomic econometric models can not provide reliable forecasts about the future. That is that the macroeconomic time series are typically generated by non-ergodic stochastic processes– as can be seen if on merely tests these for unit roots. I have made this non-ergodic criticism almost two decades ago — but you fail to cite my publication of this problem.

    • November 21, 2016 at 3:27 pm

      P Davidson—I actually know that while Brian Arthur (SFI , ‘path dependence in economics’) gets more credit or citations, you were also on this topic.

      The one problem is ‘ergodicity’ has several definitions in different contexts. eg ‘ergodicity on an attractor’ (david ruelle), chaos theory). Cosma Shalizi has discussed this (CMU-Carnegie mellon, tho I disagree with some of his papers, especially ones with Eric Smith (of SFI)—who also had a (terrible) one with Duncan Foley of NSSR). ) https://bactra.org/notebooks

      • Paul Davidson
        November 21, 2016 at 5:46 pm

        I am using the definition of ergodic as specified by Yaglom.

        Wikipedia identifies Yaglom as someone who received several prestigious awards including
        (1) in 1988 The American Physical Structural Society’s Laporte Award for his “fundamental
        contributions to statistical theory “ and (2) posthumously in 2008 the European Geoscience Union’s Richardson medal for his “eminent and pioneering contribution to the development of statistical theories….including…stochastic …models”..

        I think Yaglom’s definition should overwhelm the n’s you are citing!!!

  3. November 21, 2016 at 3:13 pm

    the only ones on this list I have really looked at or read (tho barely remember them) are Edward Leamer (eg on stolper-samuleson theorem;

    I think the last paper samuelson wrote in AER (Am Ec Rev ) basically said his theorem was ‘inapplicable’ to the real world. Its like an ‘ideal gas model’ (Boltzmann—very few gases are ‘ideal’). It assumed for example that a) the world world was at full employment , and b) there was no population growth. (I think world population has grown since 1930—probably went from 2 billion to 7 billion). He also didn’t look at technological changes.

    Its funny that P Krugman was using the Stolper-Samuelson theorem to argue for free trade in popular articles. I have an old one from 90’s in Scientific American where he says this. If you look at his technical articles in say J Political Economy he says the same thing, except he also notes that this conclusion does not follow from his equations (which he stole from theoretical physics, tho didn’t understand them and don’t derive them either.)

    and David Freedman (for a minute I thought this was a reference to M Friedman’s son, who didn’t impress me–my father took a few classes with m friedman, and he wasn’t impressed by him—they are half ideologues.)

  4. Paul Davidson
    November 21, 2016 at 6:02 pm

    Let me emphasize that I am using the definition of ergodic and nonergodic developed by Yaglom and Wold — both world recognized experts in stochastic theory. Wold contribution to stochastic theory should be known to all.

    As far as Yaglom is concerned, he may be less known to us in the USA but see Wikipedia.Wikipedia identifies Yaglom as someone who received several prestigious awards including
    (1) in 1988 The American Physical Structural Society’s Laporte Award for his “fundamental
    contributions to statistical theory “ and (2) posthumously in 2008 the European Geoscience Union’s Richardson medal for his “eminent and pioneering contribution to the development of statistical theories….including…stochastic …models”.

    As recognized experts in stochastic theory, I think the Wold and Yaglom agreed upon definition of ergodic and nonergodic for stochastic theory should outweigh the Ruelle and Shalizi reinterpretations that they need to support their more questionable analysis.

    I hope you will agree
    .

  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 )

Twitter picture

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

Facebook photo

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

Google+ photo

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

Connecting to %s