What executives get wrong about statistics: Moving from statistical significance to effect sizes and practical impact

Brian S. Anderson

Business Horizons, 2022, vol. 65, issue 3, 379-388

Abstract: Statistical significance functions as an arbiter of sorts for data analysis purporting to show a relationship between two or more variables. Unfortunately, in far too many situations, statistical significance may lead decision-makers relying on data and analytics to improve business decisions astray, particularly in the context of big data. In this article, I outline reasons why executives should develop a healthy discernment when they see the phrase “statistically significant” in media outlets, internal analyses, consulting reports, and other sources. To overcome the limitations of focusing on statistical significance, I propose executives shift their attention toward the effect size reported from a statistical model. While not without limitation, effect sizes are more useful to decision-makers, highlight the practical implication of analyses, and help in quantifying the uncertainty inherent to working with data.

Keywords: Statistical significance; Statistical correlation; Data analysis; Omitted variables; P value (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S000768132100094X
Full text for ScienceDirect subscribers only

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:eee:bushor:v:65:y:2022:i:3:p:379-388

DOI: 10.1016/j.bushor.2021.05.001

Access Statistics for this article

Business Horizons is currently edited by C. M. Dalton

More articles in Business Horizons from Elsevier
Bibliographic data for series maintained by Catherine Liu ().