Measuring Same-Sex Couples: Results from a Split-Panel Test of Alternative Relationship and Marital Status Questions

• Activity Number: 148
• Type: Invited
• Date/Time: Monday, August 4, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Government Statistics Section
• Author(s): Nancy Bates*+ and Jamie Lewis Thomas and Matthew Streeter and Shawn Bucholtz
• Companies: U.S. Census Bureau and U.S. Census Bureau and U.S. Census Bureau and U.S. Department of Housing and Urban Development
• Keywords: same-sex couples ; relationships ; measurement error ; cohabitation

Abstract

In this paper, we share results from a split-panel experiment conducted during the 2013 American Housing Survey (AHS). The AHS experimental panel tested new relationship, marital status, and cohabitation questions aimed at reducing measurement error in counting same-sex couples. The relationship item contained new categories to reflect both same and different-sex spouses and unmarried partners. The cohabitation questions aimed to 1) directly measure cohabiting couples, and 2) measure couples in new legally-recognized relationships (i.e. domestic partnerships and civil unions). The new questions were developed as part of an interagency working group on Measuring Relationships in Federal Household Surveys (MRFHS). We compare estimates from the new questions to the control panel consisting of currently-used relationship and marital status items. We conclude with a discussion of how our results fit into the larger federal statistical community and the need for consistent measures going forward.