Big Data and the Challenge of Construct Validity
- 1 March 2015
- journal article
- editorial
- Published by Cambridge University Press (CUP) in Industrial and Organizational Psychology
- Vol. 8 (4) , 521-527
Abstract
One important issue not highlighted by Guzzo, Fink, King, Tonidandel, and Landis (2015) is that simply establishing construct validity will be significantly more challenging with big data than ever before. One needs to only look as far as the other social sciences analyzing big data (e.g., communications, economics, industrial engineering) to observe the difficulty of making valid claims as to what measured variables substantively “mean.” This presents a significant hurdle in the application of big data to organizational research questions because of the critical importance of demonstrating validity in the organizational sciences as highlighted by Guzzo et al.Keywords
This publication has 19 references indexed in Scilit:
- When teams shift among processes: Insights from simulation and optimization.Journal of Applied Psychology, 2014
- Teams in Organizations: From Input-Process-Output Models to IMOI ModelsAnnual Review of Psychology, 2005
- Is More Ever Too Much? The Number of Indicators per Factor in Confirmatory Factor AnalysisMultivariate Behavioral Research, 1998
- MISSING DATA: A CONCEPTUAL REVIEW FOR APPLIED PSYCHOLOGISTSPersonnel Psychology, 1994
- Assessing Construct Validity in Organizational ResearchAdministrative Science Quarterly, 1991
- Construct Validity: A Review of Basic Issues and Marketing PracticesJournal of Marketing Research, 1981
- A QUANTITATIVE APPROACH TO CONTENT VALIDITY1Personnel Psychology, 1975
- Retranslation of expectations: An approach to the construction of unambiguous anchors for rating scales.Journal of Applied Psychology, 1963
- Convergent and discriminant validation by the multitrait-multimethod matrix.Psychological Bulletin, 1959
- Construct validity in psychological tests.Psychological Bulletin, 1955