n≥30 vs. n=all: Büyük Veri, Veri Obezitesi ve Kaybolan Nedensellikler

Altuğ Yalçıntaş

Yildiz Social Science Review, 2018, vol. 4, issue 2, 153-166

Abstract: Economists have long been criticized based on the fact that the assumptions of the theoretical models in economics are not always realistic. Big data analysis can be an opportunity for economists to fix this problem. I disagree. While big data analysts, to a large extent, need all available data (i.e. n=all) for the models to reach useful conclusions, I argue, they are not always interested in explaining causes and causal relations among variables. Instead, big data analysts strive for revealing correlations among events. Big data models that require n=all to produce useful conclusions lead to data obesity in economics where researchers turn into blind empiricists who look for correlations, rather than causations, within massive data sets. As a result of big data analyses, causes and causal effects may soon disappear from the scientific discourse. Big data analyses can cause economics to replace why-questions with what questions.

Keywords: big data in economics; data obesity; correlation; causationJournal: Yildiz Social Science Review (search for similar items in EconPapers)
JEL-codes: F00 F30 G00 G10 K00 K20 M00 M20 O10 (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://yssr.yildiz.edu.tr/storage/upload/pdfs/1628148486-tr.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aye:journl:v:4:y:2018:i:2:p:153-166

Access Statistics for this article

More articles in Yildiz Social Science Review from Yildiz Technical University Contact information at EDIRC.
Bibliographic data for series maintained by Murat DONDURAN ().