|
Activity Number:
|
273
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #303836 |
|
Title:
|
Effects of Imputation on CPS Income and Poverty Series: 1981 - 2007
|
|
Author(s):
|
Joan L. Turek*+ and Sameer Desale and Charles T. Nelson and Fritz Scheuren
|
|
Companies:
|
U.S. Department of Health and Human Services and Synectics for Management Decisions, inc. and U.S. Census Bureau and NORC at the University of Chicago
|
|
Address:
|
P.O. Box 99, Harwood, MD, 20776,
|
|
Keywords:
|
Imputation ; income ; poverty ; time series analysis ; methodology ; Current Population Survey
|
|
Abstract:
|
The Current Population Survey (CPS) has been the source of the official U.S. poverty estimates since their inception. Since then, many changes have occurred in society and in the willingness of CPS respondents to report the cash income used to construct these poverty figures. Improvements have also occurred in the CPS data collection instruments. We believe the series of annual CPS cross-sections provide a meaningful measure of changes in poverty. The current paper examines trends in poverty rates by type of imputation from 1981 until 2007 focusing particularly on how poverty series for reporters and for those with item and whole imputes have trended over this period. Differences for blacks and whites are also presented. This paper provides a beginning analysis of a detailed reconstruction of imputation and poverty series for the period 1976 to 2007.
|
