Test Objective

• In January through March of 2006, the American Community Survey (ACS) conducted the first test of new and modified content since the ACS reached full implementation levels of data collection. The results of that testing will determine the content for the 2008 ACS.
• The purpose of this report is to evaluate a modified or test version of the current item used to identify the number of vehicles available to a household in the American Community Survey (ACS). The test version for vehicles was designed to clarify the question for respondents and to save questionnaire space.

Methodology

• The Content Test compared two versions of the question on the number of vehicles available for household use. The control version replicated the wording and response categories used in the current ACS question. The test version added the term “SUVs”, an instruction to exclude motorcycles and other recreational vehicles, and changed the categorical response approach to a write-in approach.

Research Questions and Results

• Research Question 1: Do the changes to the vehicle question affect the item nonresponse rate?
  The results do not support the hypothesis that the item non-response rate will be equal to or less than the rate for the control version. Item non-response rates for the test version were higher than those for the control version. Although those differences are statistically significant, they are not considered analytically significant. Note that the item nonresponse rates for both control and test were less than 2.5 percent.
• Research Question 2: Do the changes affect the distribution of the number of vehicles reported?
  The results show that the changes included in the test version had no impact on the distribution of number of vehicles available.

Summary of Empirical Results

The empirical results show that the test version had no impact on the distribution of the number of vehicles. However, the test version neither reduced nor improved the item nonresponse rate. There is no empirical evidence to suggest that the test version performed any better than the control version.