RTI uses cookies to offer you the best experience online. By clicking “accept” on this website, you opt in and you agree to the use of cookies. If you would like to know more about how RTI uses cookies and how to manage them please view our Privacy Policy here. You can “opt out” or change your mind by visiting: http://optout.aboutads.info/. Click “accept” to agree.
The Computerized Delivery Sequence (CDS) file contains listings for nearly all addresses in the United States. Survey researchers use the CDS as a sampling frame from which to draw an address-based sample (ABS). More than 700,000 addresses on the CDS are marked as drop points, which are mail receptacles shared by multiple housing units (drop units). Drop points are a challenge to sample and present a potential source of error because of their "one-to-many" relationships. Several techniques have been developed to overcome this challenge, including deleting them from the frame or sampling all units at a given drop point. This paper serves as an introduction to these challenges, discusses the pros and cons to each "solution," and provides a list of best practices.