Abstract
A simple lemma is derived to support the claim that regression models can be manipulated to a very large extent: by simply adding one regressor one can obtain essentially every set of desired regression coefficients and predictions as well ast-values and standard errors. Consequently, if the product of a specification search is not shown to be generalizable, a sceptical attitude towards its validity is well-founded.
Similar content being viewed by others
References
Carabelli AM (1988) On Keynes's method. MacMillan Press, London
Cooley TF, LeRoy SF (1981) Identification and estimation of money demand. The American Economic Review 71:825–844
Diaconis P (1985) Theories of data analysis: From magical thinking through classical statistics. In Hoaglin DC et al (eds) Exploring Data Tables, Trends and Shapes, 1–36 John Wiley New York
Dijkstra TK (in preparation) Frequentist inference with data-instigated models, a conditional approach
Ehrenberg ASC (1968) The elements of law-like relationships. Journal of the Royal Statistical Society A 131:280–302
Friedman M, Schwartz AJ (1991) Alternative approaches to analyzing economic data. The American Economic Review 81:39–49
Goldberger AS (1989) ET Interview (by Kiefer NM). Econometric Theory 5:133–160
Hendry DF (1987) Econometric methodology: A personal perspective. In: Bewley TF (ed) Advances in Econometrics Fifth World Congress, volume II 29–48 Cambridge University Press Cambridge
Hendry DF, Mizon GE (1990) Procrustean econometrics: On stretching and squeezing data. In: Granger CWJ (ed) Readings in Econometric Methodology 121–136 Oxford University Press Oxford
Leamer EE (1978) Specification searches. John Wiley New York
Simon HA (1977) On judging the plausibility of theories. In: Ijiri Y, Simon HA. Skew Distributions and the Sizes of Business Firms 109–134 North-Holland Amsterdam
Suppes P (1985) Probabilistic metaphysics. Basil Blackwell Oxford
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dijkstra, T.K. Pyrrho's lemma, or have it your way. Metrika 42, 119–125 (1995). https://doi.org/10.1007/BF01894292
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01894292