Public Opinion Quarterly Advance Access originally published online on May 28, 2009
Public Opinion Quarterly 2009 73(2):361-367; doi:10.1093/poq/nfp018
| ||||||||||||||||||||||||||||||||||||||||||||||||
Can A Deadline and Compressed Mailing Schedule Improve Mail Response in the Decennial Census?
Address correspondence to Elizabeth Martin; e-mail: betsy{at}folhc.org.
This study reports results of a national mailout–mailback experiment that evaluated the effects of a deadline and compressed mailing schedule on response to census mail questionnaires. The experiment finds that providing a deadline and shorter interval (by one week) in which to complete the census form leads to a significantly higher rate of response (by 2.0 percentage points). Data quality was not impaired and in some cases showed significant improvements in the experimental panel (lower item nonresponse for one item and slight improvements in coverage). These results contrast with previous studies suggesting that a due date is not effective for improving response in mail surveys, and imply that a deadline would lead to significant cost savings in the decennial census.
ELIZABETH MARTIN is retired from the U. S. Census Bureau, Suitland, MD, USA. Thanks to Don Dillman for collaborating on the questionnaire design, to Pamela Giambo and David Cantor for managing the project for Westat, to Kathleen Styles, Chad Russell, and Ann Dimler for providing significant support, to Bob Fay for advice on sample design and calculation of variances, to Tammy Adams, Danny Childers, Don Dillman, Eleanor Gerber, and Jim Treat for helpful comments on earlier drafts, and to Cynthia Rothhaas and Eli Krejsa for checking and correcting tabulations and providing useful comments. The research was conducted while the author was employed by the U.S. Census Bureau, which funded the study.