Methodological note: allocation of disability items in the American Community Survey

Area of Science:

• Survey methodology
• Disability research
• Data analysis

Background:

• Prevalence and correlates of disability are determined using sample surveys.
• Allocation procedures are common for handling missing or inconsistent survey responses to create complete datasets.

Purpose of the Study:

• To examine how six disability-related questions differ in allocation rates.
• To assess the sensitivity of research findings to data allocation procedures, particularly for non-methodologists using large disability datasets.

Main Methods:

• Utilized 2010 1-year Public Use Microdata Sample files from the American Community Survey (ACS).
• Investigated allocation rates for self-care, hearing, vision, independent living, ambulatory, and cognitive ability disability items.
• Analyzed variations in allocation rates by demographic characteristics and potential influence on multivariate results.

Main Results:

• Detectable patterns exist in disability item allocation within ACS data.
• Higher allocation rates were observed for mail surveys, males, older individuals, non-English proficient groups, US citizens, Latinos, and those in or near poverty.
• Multivariate models may be sensitive to the treatment of allocated values.

Conclusions:

• Allocation rates vary based on demographic variables, methodological procedures, and survey participation behaviors.
• The potential impact of allocation rates on research and policy concerning the disabled population necessitates further investigation.