The trouble with econometrics

17 December, 2016 at 10:14 | Posted in Statistics & Econometrics | 1 Comment

0In the process of translating a theory into implications about data, so many auxiliary assumptions are made that all contact with reality is lost. Any conflict can be resolved by adjusting the auxiliary assumptions. For example, suppose we want to learn if a production process satisfy diminishing, constant, or increasing returns to scale. The issue is of substantial significance from the point of view of theory. In carrying out the test, we assume a particular form of a production function, a particular way in which stochastic errors enter, and particular ways to aggregate and measure factors of production. The result of the test has no credibility, because we do not know what we are rejecting or accepting: the theory, or the auxiliary assumptions, or the ingenuity of the econometrician.

Asad Zaman

Another prominent trouble with econometrics is the way the so called error term is interpreted. Mostly it is seen to represent the effect of the variables that were omitted from the model. The error term is somehow thought to be a ‘cover-all’ term representing omitted content in the model and necessary to include to ‘save’ the assumed deterministic relation between the other random variables included in the model. Error terms are usually assumed to be orthogonal (uncorrelated) to the explanatory variables. But since they are unobservable, they are also impossible to empirically test. And without justification of the orthogonality assumption, there is as a rule nothing to ensure identifiability:

overconfidenceWith enough math, an author can be confident that most readers will never figure out where a FWUTV (facts with unknown truth value) is buried. A discussant or referee cannot say that an identification assumption is not credible if they cannot figure out what it is and are too embarrassed to ask.

Distributional assumptions about error terms are a good place to bury things because hardly anyone pays attention to them. Moreover, if a critic does see that this is the identifying assumption, how can she win an argument about the true expected value the level of aether? If the author can make up an imaginary variable, “because I say so” seems like a pretty convincing answer to any question about its properties.

Paul Romer


1 Comment

  1. In the above quote of Zaman, the source of his purported knowledge of “reality” is obscure. Instead of trying to interpret empirical observations, he seems to base his understanding of the world merely on his own intuition or divine revelation.
    There are warnings in the Bible against this approach:
    Job 38: The LORD answered Job out of the storm…”Where were you when I laid the foundation of the earth? Tell me if you have such insight… Do you know the laws of the sky or make them rule the earth?”
    1 Corinthians 13:12: St. Paul: “Now we see through a glass darkly. When Jesus returns to Earth we will see very clearly. Now my knowledge is incomplete.”
    Bertrand Russell described how we struggle to understand the world:
    “The development of science out of common sense has not been by way of a radical new start … but rather by way of successive approximations.
    … The actual procedure of science consists of an alternation of observation, hypothesis, experiment, and theory.
    … When a theory fits a number of facts, but goes slightly astray with regard to certain others, it happens generally, though not always, that it can be absorbed, by a slight modification, into a new theory which includes the hitherto discrepant facts.”
    Bertrand Russell: The Analysis of Matter [1927] p. 193-4.

Sorry, the comment form is closed at this time.

Create a free website or blog at
Entries and comments feeds.