|
Activity Number:
|
66
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #305919 |
|
Title:
|
Nonresponse Bias Studies: 2003--2004 School and Staffing Survey
|
|
Author(s):
|
Robyn Sirkis*+ and Bac Tran and Phyllis Singer
|
|
Companies:
|
U.S. Census Bureau and U.S. Census Bureau and U.S. Census Bureau
|
|
Address:
|
4700 Silver Hill Road, Washington, DC, 20233,
|
|
Keywords:
|
nonsampling ; nonresponse ; bias ; substantive difference ; SASS
|
|
Abstract:
|
Nonresponse error is one kind of nonsampling error. Nonresponse error is a function of response rates and the differences in responses between respondents and nonrespondents. A low response rate cannot cause bias alone, however it suggests the potential for bias to occur. Nonresponse error can also cause misinterpretation of the results published. The Office of Management and Budget (OMB) is considering a mandate to conduct nonresponse bias studies if the expected unit response rate is below 80 percent and the expected item response rate is below 70 percent. The National Center for Education Statistics requested that a Nonresponse Bias Study be conducted for the 2003-2004 School and Staffing Survey. Our discussion focuses on portions of the methodology applied, results, lessons learned, as well as future endeavors for nonresponse bias studies.
|
