• Presentation

Supplementing Address-Based Sampling Frames with Physical Addresses of Housing Units with Unlocatable Mailing Addresses

Citation

Shook-Sa, B. E., & Currivan, D. B. (2011, May). Supplementing Address-Based Sampling Frames with Physical Addresses of Housing Units with Unlocatable Mailing Addresses. Presented at AAPOR 2011, Phoenix, AZ.

Abstract

When utilizing an address-based sampling (ABS) frame for an in-person household survey, households with unlocatable mailing addresses are a primary source of undercoverage. Unlocatable mailing addresses such as post office boxes, rural route boxes, highway contract boxes, and simplified addresses cannot be linked to housing units on the ground. For this reason, approximately two million residential unlocatable mailing addresses are typically excluded from the national ABS frame for in-person surveys. Most of the undercoverage occurs in rural areas where unlocatable addresses are more prevalent. Low ABS coverage in rural areas often leads researchers to resort to a hybrid frame that supplements ABS coverage with costly field enumeration (FE) methods in areas without adequate ABS coverage.

Databases of listed addresses derived primarily from white pages contain physical addresses for a significant number of households with unlocatable mailing addresses. We explore the feasibility of white page supplementation using data from the 2009 National Survey on Drug Use and Health (NSDUH). The NSDUH provides national, state, and substate data on substance use and mental health in the civilian, non-institutionalized population age 12 and older. Data are collected on a quarterly basis each year, with approximately 140,000 household screenings and 67,500 interviews completed annually.

We estimate the gains in coverage provided by white page supplementation and evaluate the feasibility of combining white page lists with the locatable mailing addresses on the ABS frame. We also investigate the decreased reliance on FE that results from white page supplementation in a hybrid frame approach. We estimate that white page supplementation could add as much as 7.6 percent coverage to the household population in rural segments. This would result in cost savings by reducing the number of segments that need to be field enumerated.