Reanalysis of Privacy Survey

• Activity Number: 172
• Type: Topic Contributed
• Date/Time: Tuesday, August 13, 2002 : 8:30 AM to 10:20 AM
• Sponsor: Section on Government Statistics*
• Author(s): Carla Inclan*+ and Gautam Jaggi and Kristin Valente
• Affiliation(s): Ernst & Young, LLP and Ernst & Young, LLP and Ernst & Young, LLP
• Keywords: Privacy ; sampling weights ; classification tree models

Abstract

Consumers' attitudes towards privacy and the use of personal information are the subject of a recent nationwide survey conducted by Privacy & American Business and Harris Interactive, under the sponsorship of Ernst & Young and the American Institute of Certified Public Accountants (AICPA). The survey intends to identify the steps that businesses can take to establish trust and confidence in privacy policies with consumers, and further determine what behavior changes consumers claim to exhibit when trust and confidence in privacy policies is achieved. We undertake a further analysis of the results of that survey to identify particular demographic groups of consumers who share the same views and concerns. Businesses, particularly those who actively participate in e-commerce, are interested in identifying the actions necessary to address the privacy concerns of specific demographic groups that they target and to determine the expected return on the investment in those actions with those consumers. We use classification tree models to search for those groups of consumers. Particular attention is paid to the use of survey weights when estimating the tree models.