Lars Syll summarizes: “Yes, indeed, econometrics fails miserably over and over again.”
To be sure, it is NOT econometrics that fails but scientifically incompetent economists that fail for 200+ years.
There are theoretical economics and political economics. The goal of theoretical economics is the true theory about how the actual economy works. Scientific truth is well-defined: “Research is in fact a continuous discussion of the consistency of theories: formal consistency insofar as the discussion relates to the logical cohesion of what is asserted in joint theories; material consistency insofar as the agreement of observations with theories is concerned.” (Klant, 1994). Logical consistency is secured by applying the axiomatic-deductive method and empirical consistency is secured by applying state-of-the-art testing.
Economists fail on both counts. Orthodox and heterodox economists are simply too stupid to apply scientific methods correctly. Needless to emphasize that they always blame the tools for their failure. It is a curious fact that statistics, testing, mathematics, and axiomatic-deductive logic work well in the successful sciences but NOT in the failed science of economics. Economists, of course, have a thousand excuses for why they fail.#1
Sander Greenland comes up with this insight about the axiomatic-deductive method: “… since a deduction produces certainty about the real world only when its assumptions about the real world are certain.”
This is known for more than 2300 years ― except to economists: “When the premises are certain, true, and primary, and the conclusion formally follows from them, this is demonstration, and produces scientific knowledge of a thing.” (Aristotle)
Neither Orthodoxy nor Heterodoxy is based on certain, true, and primary premises and this is why neither statistics nor mathematics nor logic work in economics. To be clear, this is NOT the fault of statistics or mathematics, or logic. More precisely, the foundational assumptions, a.k.a. axioms, of Walrasianism, Keynesianism, Marxianism, and Austrianism are provably false. Because of this, NOTHING of scientific value will ever come from it.