The 2010 Census Alternative Questionnaire Experiment: Replication of the 2000 Census Questionnaire

• Activity Number: 396
• Type: Topic Contributed
• Date/Time: Tuesday, July 31, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Courtney Reiser*+
• Companies: U.S. Census Bureau
• Keywords: Census ; questionnaire design ; item nonresponse ; self-response

Abstract

Traditionally, the Census Bureau has conducted an experiment during the decennial census to evaluate the cumulative effects of all content changes to the questionnaire from the previous census. The most recent chapter of this tradition was conducted as part of the 2010 Census Alternative Questionnaire Experiment. Specifically, research was conducted to compare the results from a control panel using the 2010 Census questionnaire to the results from a questionnaire that replicated the Census 2000 questionnaire wording, categories, order, and other essential design features. A number of changes were made to the 2010 Census questionnaire, compared to the form used in Census 2000. In addition to changes in the overall questionnaire format and appearance, almost every census data item underwent at least some change in terms of question wording, response categories, and/or instructions. By comparing the Census 2000-style questionnaire with the 2010 Census questionnaire in the same timeframe, we were able to eliminate the impact of real changes to the population to more clearly assess the combined effects of the questionnaire design changes. This paper describes the results of the experiment.