Data mining and the econometrics industry: comments on the papers of Mayer and of Hoover and Perez

Journal of Economic Methodology 05/2000; 7(2):211-216. DOI: 10.1080/13501780050045092


We maintain that the actions of researchers show that data mining is a necessary part of econometric inquiry. We analyse this phenomenon using the analogy of an industry producing a product (econometric analyses). There is a risk of selective reporting as Mayer indicates but we argue that other researchers (competition) will ensure that the sensitivity of truly important findings is checked. Hence, initial researchers have an incentive to analyse sensitivity from the beginning and so produce a quality product. Some suggestions are made towards encouraging this process. The 'general to specific' approach to data mining as promoted by Hoover and Perez can be valuable but it is premature to eliminate other strategies.

7 Reads
  • Source

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The Representational Theory of Measurement conceives measurement as establishing homomorphisms from empirical relational structures into numerical relation structures, called models. Models function as measuring instruments by transferring observations of an economic system into quantitative facts about that system. These facts are evaluated by their accuracy. Accuracy is achieved by calibration. For calibration standards are needed. Then two strategies can be distinguished. One aims at estimating the invariant (structural) equations of the system. The other is to use known stable facts about the system to adjust the model parameters. For this latter strategy, the requirement of models as homomorphic mappings is not required anymore.
  • [Show abstract] [Hide abstract]
    ABSTRACT: It has been over 70 years since Erich Fromm wrote “Escape From Freedom.” He defined two types of freedom: freedom from (negative) and freedom to (positive). Fromm’s masterpiece, however, does not measure the two types of freedom, and this is not surprising—there were no freedom data at the time. Now, there are plenty of data, and Fromm’s concepts of freedom can be operationalized across countries. The two types of freedom, positive and negative, correlate at below 0.5, and such low correlation is surprising—I discuss outliers and point out that freedom is an end in itself, as recognized, for instance, by Amartya Sen. Furthermore, while we acknowledge the importance of freedom from, we forget that freedom from is not fully realized without freedom to: it’s great to be free; but it’s even better to feel free as well.
    Social Indicators Research 02/2013; DOI:10.1007/s11205-013-0473-x · 1.40 Impact Factor