In January 2013, the Census Bureau began offering respondents the option to complete the American Community Survey (ACS) over the Internet. The ACS is a national survey that collects demographic, housing, social and economic characteristics from all household members. The Census Bureau tested the feasibility of using the Internet mode during two tests that took place in 2011. Census staff evaluated the data from these tests, and the high response rates and potential cost savings encouraged Census to implement the Internet mode in 2013.

The evaluation of the 2011 test data included a review of item nonresponse rates. Matthews et al. (2012) and Tancreto et al. (2012) found that Internet returns, when compared with mail returns, had lower item nonresponse rates for basic demographic and housing items, but higher item nonresponse rates for detailed social and economic items.

The purpose of this evaluation is to document item nonresponse rates for mail and Internet returns and compare the completeness of returns by mode. This evaluation uses 2013 ACS production data and covers several survey items. The best source for comparing the completeness of item-level responses in these two modes is the final edited data but those data will not be available until we run the full set of edit and allocation programs. We plan to document and compare those final item allocation rates later this year. To preview the completeness of mail and Internet responses, we chose to calculate a set of item nonresponse rates based on incoming nonresponse before follow-up operations and editing. There are some expected limitations in using these raw response files which are detailed in the methodology section.