Implementation of an Efficient Sampling and Case Processing Method

• Activity Number: 182
• Type: Contributed
• Date/Time: Monday, August 4, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Shelton M. Jones*+ and Tenbroeck Smith and Katherine Treiman and Mai Nguyen and Connie Hobbs and Alyssa Troeschel
• Companies: RTI International and American Cancer Society and RTI International and RTI International and RTI International and American Cancer Society
• Keywords: Confidential Sampling ; NOPID sampling ; multi-site frame construction

Abstract

We describe a method for sampling and processing cases that enables researchers to efficiently and collaboratively build sampling frames in a multi-site study. This method builds the sampling frames by using data from multiple data sources, thus introducing additional variables for stratification and/or clustering. It applies the No Personal Identification Disclosed (NOPID) approach (Jones, et al, 2011) to ensure respondent confidentiality, while attempting to maximize response rates and reduce measurement error. This method was used for The Patient Reported Outcomes Symptoms and Side-Effects Study (PROSSES) funded by the American Cancer Society-a study of cancer patient symptom experiences. To maximize accurate recall of symptom experiences during curative treatment, monthly cross-sections of new cancer patients were sampled and mailed recruitment materials on a monthly basis. PROSSES was conducted with 17 cancer centers dispersed across the United States, and achieved an overall response rate of approximately 60%. We will describe the key steps to successfully fielding PROSSES based on the NOPID method as well as the challenges faced, their solutions, and the lessons learned.