Memo

The Census Bureau plans to conduct new research under the Generic Clearance for 2020 Census Field Test to Automate Field Data Collection Activities (OMB Control Number 0607-0971). The Center for Survey Measurement in conjunction with the Decennial Statistical Studies Division plans to conduct iterative small-scale mail-out tests to refine messaging in invitations to an online survey. Results from these tests will inform the 2020 Decennial Census testing program for further testing. This submission documents our second test in this series.

This test has two objectives and each objective has two treatments that are completely crossed creating a four panel test.

The first objective, called the “User ID Placement” objective, determines where to print the User ID in the mailing materials to maximize response to an online survey. The User ID is needed to gain entry to the online survey. In current decennial production tests, the User ID is printed above the bar code near the address. For the first and fourth mailings, the address, barcode, and User ID are printed on an Internet card. This card and a letter explaining the survey request are enclosed in an envelope. The address and bar code on the card show through a window in the envelope. The third and second mailings are postcards. There, the User ID is printed above the bar code and on the same side of the postcard as the address. For this test, we use the current User ID placement as our control. The other treatment includes the User ID directly on the letter in the first and fourth mailings. Those mailings will not contain an Internet card. The second and third postcard mailings will be identical to the control, with the User ID on the same side of the postcard as the address.

The second objective, called the “User ID Length” objective, determines the effect of a shorter User ID on the response rate to an online survey. Our Control treatment uses a 12–digit User ID – which is the minimum number of digits we could use for a User ID in the 2020 Census. The other treatment uses a shorter 8-character alpha-numeric User ID.

We plan to conduct this test with a Census Day of June 1, 2016. There will be a maximum of four mailings to each housing unit. The first mailing is the initial letter on May 23, 2016. The User ID placement and the User ID length will differ in the first mailing. The second mailing, occurring one week later on May 31, 2016, is a postcard. Only the User ID Length will differ on the postcard. The third mailing, on June 6, 2016, is another reminder postcard. Again, the User ID Length will differ. The fourth mailing is the final letter on June 13, 2016. The User ID placement and the User ID length will differ in the fourth mailing. The survey will close out June 27, 2016, approximately six weeks after the first mailing. The third and fourth mailings will not be sent to any housing unit for which a response has been received.

This is an online-only data collection test. There is no paper questionnaire or telephone data collection for this test. Because some sampled households might not be able to respond online, we offer a telephone number with an automated message indicating that we will contact them if we need their information if they cannot respond on the Internet.

We will select a sample of 8,000 addresses from the Census Bureau’s Master Address File. Each User ID Placement treatment will have a sample of 4,000 housing units and each User ID Length treatment will have a sample of 4,000 housing units. The design will be fully-crossed. Given a response rate between 40 and 45 percent, we should be able to detect an estimated 5 percent difference in response using alpha=0.10 and beta=0.80, adjusted for multiple comparisons. The sample will exclude housing units selected for other recent Census tests and the American Community Survey.

The online survey is similar to the 2015 National Content Test online survey used approved under the (OMB number 0607-0985) on 6/30/2018. The survey collects general demographic data.

The first enclosure includes:

• Initial Letter (showing differences for each treatment by colored text)

• Internet card (for panels without the User ID on the letter)

• Postcard Reminder (showing differences for the User ID Length by colored text)

• Second Postcard Reminder (showing differences for the User ID Length by colored text)

• Final Letter (showing differences for each treatment by colored text)

The second enclosure includes the survey questions (screenshots where available and text when the screenshot is not available).

We estimate that users will spend 10 minutes on average completing the survey and approximately 5 minutes reading mailing material. Thus, the total estimated respondent burden for this study is approximately 2,000 hours, which assumes everyone reads the mailing material and answers the survey.

The contact person for questions regarding data collection and statistical aspects of the design of this research is listed below:

Julia Coombs

Decennial Statistical Studies Division

U.S. Census Bureau

Washington, D.C. 20233

(301) 763-5747

[email protected]

2