Impact of New Income Questions on Reported Income in the National Survey on Drug Use and Health (NSDUH)

• Activity Number: 313
• Type: Contributed
• Date/Time: Tuesday, August 5, 2008 : 2:00 PM to 3:50 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Jeremy Aldworth*+ and Dicy Painter and Tania Robbins and David Heller
• Companies: RTI International and Substance Abuse and Mental Health Services Administration and RTI International and RTI International
• Keywords: Household survey ; reported income ; questionnaire change ; imputation ; Social Security ; Supplemental Security Income

Abstract

The NSDUH is an annual national survey of substance use and mental health measures in the U.S. civilian population aged 12 or older. We show that we were able to reduce the number of income questions in the 2006 NSDUH, thereby reducing respondent burden, without significantly impacting estimates of reported income. In this survey, 5.7% of the 67,802 respondents received the reduced set of questions, and analyses showed an impact in only one case. A question on Social Security income was eliminated, and as a result, it appeared to be confused with Supplemental Security Income, which was retained. A decision was made to reintroduce questions about Social Security in later surveys. Simulated imputation analyses showed that the new questions would have little impact on imputed estimates, and timing data analyses showed a 24% reduction in median time to complete the reduced set of questions.