|
Activity Number:
|
252
- SPEED:Improving Survey Data Quality with Multiple Data Sources, Administrative Data, and Nonresponse Bias Control, Part 2
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 29, 2019 : 2:00 PM to 2:45 PM
|
|
Sponsor:
|
Survey Research Methods Section
|
|
Abstract #307625
|
|
|
Title:
|
Carry Forward Imputation for Unit Non-Response After a Survey Redesign
|
|
Author(s):
|
Kimberly Ault*
|
|
Companies:
|
RTI International
|
|
Keywords:
|
multiple data sources;
imputation;
unit nonresponse;
survey redesign
|
|
Abstract:
|
Carry forward imputation can be used for unit-level survey non-response when historical data are available. Challenges for using carry forward imputation occur when a survey undergoes a redesign, since the historical data may not be most appropriate for imputation. A supplemental data source can be used to adjust the historical information. This paper discusses how CF imputation was used to impute data for all unit non-respondents in an education study after a redesign. In the current iteration, unit-level data were collected by Classification of Instructional Programs codes; whereas, for prior iterations, unit level data were collected by broad field of study codes. A supplemental data source was used to adjust the historical data by matching units and using a ratio adjustment based on the other data source to estimate unit-level changes.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2019 program
|
