The miracle of the Septuagint and the promise of data mining in economics
Stellenbosch Working Paper Series No. WP15/2006Publication date: 2006
Author(s):
This paper argues that the sometimes-conflicting results of a modern revisionist literature on data mining in econometrics reflect different approaches to solving the central problem of model uncertainty in a science of non-experimental data. The literature has entered an exciting phase with theoretical development, methodological reflection, considerable technological strides on the computing front and interesting empirical applications providing momentum for this branch of econometrics. The organising principle for this discussion of data mining is a philosophical spectrum that sorts the various econometric traditions according to their epistemological assumptions (about the underlying data-generating-process DGP) starting with nihilism at one end and reaching claims of encompassing the DGP at the other end; call it the DGP-spectrum. In the course of exploring this spectrum the reader will encounter various Bayesian, specific-to-general (S-G) as well general-to-specific (G-S) methods. To set the stage for this exploration the paper starts with a description of data mining, its potential risks and a short section on potential institutional safeguards to these problems.
JEL Classification:C11, C50, C51, C52, C87
Keywords:Data mining, model selection, automated model selection, general to specific modelling, extreme bounds analysis, Bayesian model selection
Download: PDF (359 KB)Login
(for staff & registered students)
Upcoming Seminars
Monday 28 July 202512:00-13:00
Dr Neil Rankin: Ceo Of Predictive Insights & Stellenbosch University
Topic: "TBC"
12:00-13:00
Prof Willem Boshoff: Stellenbosch University
Topic: "Two competing approaches in South African competition policy: merger control and anti-cartel enforcement over the past 30 years"
12:00-13:00
Professor Johan Fourie: Stellenbosch University
Topic: "Economic History: TBC"
BER Weekly
18 Jul 2025 Encouraging data, but messy politics while US tariff deadline loomsThe big global data prints of the week came on Tuesday, with better-than-expected Chinese GDP growth for Q2 and US core CPI coming in lower than expected, but still (finally) reflecting some signs of tariffs being passed on to consumers. Locally, the uptick in mining production and retail sales was positive for Q2 GDP dynamics. In addition to the data,...
Read the full issue
Upcoming Seminars
Monday 28 July 202512:00-13:00
Dr Neil Rankin: Ceo Of Predictive Insights & Stellenbosch University
Topic: "TBC"
12:00-13:00
Prof Willem Boshoff: Stellenbosch University
Topic: "Two competing approaches in South African competition policy: merger control and anti-cartel enforcement over the past 30 years"
12:00-13:00
Professor Johan Fourie: Stellenbosch University
Topic: "Economic History: TBC"
BER Weekly
18 Jul 2025 Encouraging data, but messy politics while US tariff deadline loomsThe big global data prints of the week came on Tuesday, with better-than-expected Chinese GDP growth for Q2 and US core CPI coming in lower than expected, but still (finally) reflecting some signs of tariffs being passed on to consumers. Locally, the uptick in mining production and retail sales was positive for Q2 GDP dynamics. In addition to the data,...
Read the full issue