Activity Number:
|
538
- Transitions from Telephone Surveys to Self-Administered and Mixed-Mode Surveys
|
Type:
|
Invited
|
Date/Time:
|
Thursday, August 11, 2022 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract #320438
|
|
Title:
|
The Impact of an RDD to ABS/Mail Sample Design and Mode Change in the 2021 New York City Community Health Survey (CHS)
|
Author(s):
|
Michael Witt* and Steven Fernandez and Stephen Immerwahr and Stas Kolenikov and Amber Levanon Seligson and Martha McRoy and John Sokolowski and Nicholas Ruther and Stephanie Zimmer
|
Companies:
|
Abt Associates and New York City Department of Health and Mental Hygiene and New York City Department of Health and Mental Hygiene and NORC and New York City Department of Health and Mental Hygiene and Abt Associates and Abt Associates and Abt Associates and Abt Associates
|
Keywords:
|
ABS Design;
Bridge Study;
Mode Change;
Mode Effect;
Splicing Trends;
Health Survey
|
Abstract:
|
The NYC Community Health Survey (CHS), conducted by the NYC Department of Health and Mental Hygiene (DOHMH), is an annual survey of ~10,000 randomly selected adult New Yorkers. The CHS helps track the health of New Yorkers and inform health policy decisions. The survey sample design and data collection protocol has historically been random digit dialing (RDD) with strictly telephone data collection. To maximize response rates and reduce data collections costs, the sample design and data collection protocol changed beginning with the 2021 survey. The 2021 sample was selected from an address-based sampling (ABS) frame and the data collection protocol involved a combination of letter and post card solicitations asking respondents to complete the survey via web followed by a paper mailing of the survey to a sample of nonrespondents. A bridge study in 2021 measured the potential effects of the design change. This paper will summarize the design and data collection protocol changes, discuss how changes might have impacted estimates, and provide recommendations and examples on how analysts might use the results of the bridge study to adjust historical estimates for trend analysis.
|
Authors who are presenting talks have a * after their name.