Home > Uncategorized > Brief history of econometrics

Brief history of econometrics

from Asad Zaman

Launched in early 20th Century by Ragnar Frisch, econometric methodology was strongly shaped by the Cowles Commission (CC) in the 1960’s. The CC approach relied on structural equations, which embodied causal information known in advanced to the researcher. The goal was estimation of causal effects, and not discovery or assessment of the hypothesized causal structures. The oil shock of the 1970’s led to dramatic failures of macroeconomic regression models, leading to general distrust of econometric methodology. Two major critiques emerged. The Sims critique argued that hypothesized causal structures were false, and should be abandoned. We should go back to a purely descriptive analysis, looking for patterns in the numbers, without any reference to the real world phenomena represented by these numbers. Directly opposite was the Lucas critique which said that regression models were based on surface relationships between the numbers and ignored the deeper causal structures which drive these relationships. Regression models would fail when economic regimes underwent structural change – precisely when they were most needed. Neither approach has led to successful macro models. Models based on both approaches, as well as more conventional macro models, failed dramatically in the Global financial crisis. The fundamental problem lies in the failure of econometrics to incorporate causal inference correctly.

Causal Explanation of Autonomy & Invariance of Regression Relationships

  1. Gerald Holtham
    April 26, 2021 at 6:46 pm

    Econometrics can’t be better than the theoretical models it is trying to implement. Since macroeconomic theory has been based on nonsensical or counterfactual premises for several decades you should not expect the models to demonstrate any ability to foretell events.
    This not a failure to incorporate causal inferences; it is incorporating erroneous causal hypotheses and refusing to abandon them in the face of contrary evidence.

    • bruceolsen
      April 26, 2021 at 8:19 pm

      The counterfactuality of neoclassical economics is orthogonal to this issue Asad Zaman is pointing out.

      Just sayin’.

  2. Gerald Holtham
    April 27, 2021 at 10:58 am

    Perhaps but he is citing as evidence for his proposition what is in fact evidence of something else.

  3. Gerald Holtham
    April 27, 2021 at 11:34 am

    For example:
    “The oil shock of the 1970’s led to dramatic failures of macroeconomic regression models, leading to general distrust of econometric methodology.”
    Oil price changes of a few percentage points had and have no perceptible macroeconomic effect. So why would a macroeconomic model include them? Even if it had, based on past data, would it have been able to predict the effect of an increase of 400 per cent? Was it supposed to include equations for the Arab-Israeli conflict? When something unprecedented happens you expect to be surprised. Model-building is not soothsaying and there is no such thing as an all-purpose model. Any model is of a particular regime addressed to particular questions. When the regime or questions change, I change the model. What do you do sir?
    This was not a failure to incorporate “causal inferences”. Before the oil shock happened there were no relevant data from which to draw any inference.
    The financial crisis is a different matter. There was already evidence that the models in use were not useful to address relevant questions. The failure that time was a failure of economics professionals. But it was not a failure of statistical inference. It was a refusal to accept existing empirical refutation of the models themselves. As Groucho Marx might have said: “are you going to believe Robert Lucas or the evidence of your own eyes?” Too many economists opted for Lucas.

  4. Gerald Holtham
    April 27, 2021 at 12:08 pm

    Here is a story readers may find interesting. I joined the OECD as an economist not so long after the first oil shock. OECD economists had analysed the shock as if it were a large tax imposed on all oil users and inferred it would reduce their expenditure on everything else. Would the oi producers increase their spending to compensate? They looked at income distribution and port facilities in Saud Arabia and concluded there was no way expenditure would or could be stepped up to compensate. They therefore predicted a substantial recession. Because of the feed-through of the price rise to other prices the recession would be accompanied by inflation in oil-importing countries – the then-unprecedented phenomenon of stagflation. When these forecast were presented at meetings to member countries there was a sharp push-back. Official bodies were not supposed to forecast recessions because that would undermine confidence and be a self-fulling prophecy. The OECD secretariat was forced to modify the forecast and show a flat economy rather than outright recession.
    The episode led to Keynesian income-expenditure analysis going out of fashion and monetarism coming in. But the OECD economists working with a broadly Keynesian framework had no trouble working out what was going on, even though they could not have predicted the shock itself. A massive negative terms of trade shock can cause stagflation and exacerbate social conflict over income shares. As my kids say: “duh”. Diagnosis does not mean cure, however, and no-one knew what to do about it. Expansionary fiscal policy to cure the recession would perpetuate the inflation, then running in double digits. Hence the popularity of Milton Friedman’s patent remedy. Volker decided crushing the inflation was the first priority and pretended he believed Friedman in order to induce another recession in 1980 and put the workers in their place, None of that would have surprised Keynes much and it would not have surprised Kalecki at all. In fact he predicted that policy priority in 1944.
    By the way, he was an economist and a great one.

  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.