|
Activity Number:
|
390
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #306279 |
|
Title:
|
Estimating Birth Counts for Small Geographical Domains Used for Control Totals in Raking Adjustment
|
|
Author(s):
|
Amang Sukasih*+ and Donsig Jang and Mary Edith Bozylinsky and Barbara L. Carlson
|
|
Companies:
|
Mathematica Policy Research, Inc. and Mathematica Policy Research, Inc. and Mathematica Policy Research, Inc. and Mathematica Policy Research, Inc.
|
|
Address:
|
600 Maryland Ave., SW, Suite 550, Washington, DC, 20024,
|
|
Keywords:
|
weighting ; estimation ; natality ; city of birth ; CDC ; fragile families
|
|
Abstract:
|
Raking is often used in survey weighting to control the distribution of the sample so that it is consistent with some known population distributions or totals by key variables. Such control totals are usually obtained from the sample frame or external data; however, domains available are sometimes not exactly matched to domains of interest. CDC natality data is a good source for population birth totals. Data on place of birth (state and county) are available. However, the same variable for smaller geographical units like city is not available, yet often some policy research studies need such birth totals by city of birth. The Fragile Families Survey is one example where births were sampled within hospitals within selected cities, and city-level analysis was of primary interest. We will explain how weighting, raking, and creating synthetic estimates of total births by city were done.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2006 program |