by Milton Friedman’s critique of econometrics Tinbergen’s results cannot be judged by ordinary tests of statistical significance. The reason is that the variables with which he winds up, the particular series measuring these variables, the leads and lags, and various other aspects of the equations besides the particular values of the parameters (which alone can be tested by the usual statistical technique) have been selected after an extensive process of trial and error because they yield high coefficients of correlation. Tinbergen is seldom satisfied with a correlation coefficient less than 0.98. But these attractive correlation coefficients create no presumption that the relationships they describe will hold in the future. The multiple regression equations which yield them are simply tautological reformulations of selected economic data. Taken at face value, Tinbergen’s work “explains” the errors in his data no less than their real movements; for although many of the series employed in the study would be accorded, even by their compilers, a margin of error in excess of 5 per cent, Tinbergen’s equations “explain” well over 95 per cent of the observed variation. As W. C.
Topics:
Lars Pålsson Syll considers the following as important: Statistics & Econometrics
This could be interesting, too:
Lars Pålsson Syll writes The history of econometrics
Lars Pålsson Syll writes What statistics teachers get wrong!
Lars Pålsson Syll writes Statistical uncertainty
Lars Pålsson Syll writes The dangers of using pernicious fictions in statistics
Milton Friedman’s critique of econometrics
Tinbergen’s results cannot be judged by ordinary tests of statistical significance. The reason is that the variables with which he winds up, the particular series measuring these variables, the leads and lags, and various other aspects of the equations besides the particular values of the parameters (which alone can be tested by the usual statistical technique) have been selected after an extensive process of trial and error because they yield high coefficients of correlation. Tinbergen is seldom satisfied with a correlation coefficient less than 0.98. But these attractive correlation coefficients create no presumption that the relationships they describe will hold in the future. The multiple regression equations which yield them are simply tautological reformulations of selected economic data. Taken at face value, Tinbergen’s work “explains” the errors in his data no less than their real movements; for although many of the series employed in the study would be accorded, even by their compilers, a margin of error in excess of 5 per cent, Tinbergen’s equations “explain” well over 95 per cent of the observed variation.
As W. C. Mitchell put it some years ago, “a competent statistician, with sufficient clerical assistance and time at his command, can take almost any pair of time series for a given period and work them into forms which will yield coefficients of correlation exceeding ±.9 …. So work of [this] sort … must be judged, not by the coefficients of correlation obtained within the periods for which they have manipulated the data, but by the coefficients which they get in earlier or later periods to which their formulas may be applied.” But Tinbergen makes no attempt to determine whether his equations agree with data other than those which they translate …
The methods used by Tinbergen do not and cannot provide an empirically tested explanation of business cycle movements.
It is usual in macroeconomic (media) discourses to put Keynes and Fredman as bitter enemies. But on some issues they are in fact very close to each other. Econometrics, and especially its limited applicability, is — as can be seen comparing Friedman’s critique above to Keynes’ critique — one such prominent case.