Perspectives: Measure proliferation in advertising research: are standard measures the solution?

Abstract

Recent research has found considerable measure proliferation (i.e., the same construct is measured in multiple different ways) in advertising research. Measure proliferation increases the risk of using invalid measures, may render research results incommensurable across studies, opens up for ‘p-hacking’, and causes practical problems for researchers. Standard measures of advertising constructs would solve many of these issues but raises other issues such as what criteria to rely on when developing and evaluating measures. This paper discusses problems associated with measurement proliferation, challenges when introducing standard measures, and outlines a way forward for advertising research. It is suggested that advertising research can progress towards standard measures by gradually introducing three new journal publication requirements over an extended period of time: 1) full disclosure of measurement information, 2) all measures should be formally validated, and 3) standard measures should be used in all studies (with justifiable exceptions). In addition, the paper discusses further research that would support the introduction of the new publication requirements.

Keywords:

• Measurement
• psychometrics
• standard measures
• P-hacking
• methodology

Acknowledgement

The author is grateful to the Editor of IJA, Ray Taylor, for valuable feedback on an earlier version of this paper.

Disclosure statement

No potential conflict of interest was reported by the author.

Additional information

Notes on contributors

Lars Bergkvist

Lars Bergkvist is a professor of marketing in the College of Business at Zayed University, Abu Dhabi, United Arab Emirates. His primary research interests are advertising, leveraged marketing communications, and research methodology.