IAB Report Finds Online Ad Research Wanting
August 6 2010
The Interactive Advertising Bureau (IAB) has released a damning report on the methodology used for online site intercept studies for ad effectiveness. The study found major problems including 'extremely low response rates', the use of 'quasi-experimental research designs' and dubious weighting adjustments.
The publication, An Evaluation of Methods Used to Assess the Effectiveness of Advertising on the Internet, is billed as 'the first thorough, public assessment undertaken of the state of online ad effectiveness research'.
Author Paul Lavrakas, Ph.D., is a former Chief Research Methodologist for the Nielsen Company and the author of numerous publications including Telephone Survey Methods: Sampling, Selection, and Supervision, as well as four other books covering election polling and the news media.
Dr. Lavrakas conducted 'a detailed review of relevant academic literature' and multiple interviews with experts at research vendors and media companies, and concluded that the validity of most current
Interactive Advertising Effectiveness (IAE) research is 'threatened' or 'compromised' by:
- the extremely low response rates achieved, especially where subsamples are required
- 'the near-exclusive use of quasi-experimental research designs rather than classic experimental designs', and
- 'a lack of valid empirical evidence that the statistical weighting adjustments... adequately correct for the biasing effects' created by the two preceding issues.
Interviews with researchers suggested they were aware of these flaws but were prevented from rooting them out by considerations of expense, according to Dr. Lavrakas.
Meanwhile the IAB also announced that it would be leading an industry effort and further research to promote the use of established principles for the conduct of market and consumer research in brand-effectiveness studies. Its plans include the launch of a cross-industry task force to help understand the impact of these studies on the online ad community's broader supply chain, and minimize inefficiencies they may create; and the drawing up of a set of US best practices for online brand impact ad effectiveness studies.
Sherrill Mane, the IAB's SVP of Industry Services, commented: 'If the phrase 'marketing science' is to have any meaning, participants in the ecosystem must demand that their vendors employ rigorous, tested research methodologies, even if doing so costs more'.
Dan Murphy, SVP of Interactive Research and Ad Traffic at Univision, and a member of the IAB Research Council, comments: 'There is an enormous volume of brand impact studies being conducted across online media, and we developed this initiative because we saw a marketplace need to help all industry stakeholders identify the correct execution and best practices around their use'.
Founded in 1996 and headquartered in New York City, the IAB comprises more than 460 leading media and tech companies responsible for selling an estimated 86% of US online advertising.
Details of the above study are at
www.iab.net/interceptstudies which the IAB's Research Council can be found at
www.iab.net/member_center/councils_committees_working_groups/councils/research_council .
All articles 2006-23 written and edited by Mel Crowther and/or Nick Thomas, 2024- by Nick Thomas, unless otherwise stated.
