Abstract #301405

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #301405
Activity Number: 435
Type: Topic Contributed
Date/Time: Thursday, August 7, 2003 : 8:30 AM to 10:20 AM
Sponsor: Section on Survey Research Methods
Abstract - #301405
Title: Simplified Methods of Inference for the Survey of Income and Program Participation: An Alternative for Public Users
Author(s): Reid Rottach*+ and David Hall
Companies: U.S. Census Bureau and U.S. Census Bureau
Address: DSMD, Washington, DC, 20233-8700,
Keywords: variance estimation ; degrees of freedom ; complex sample design ; balanced repeated replication (BRR) ; generalized regression ; linearization
Abstract:

Data analysis for the Survey of Income and Program Participation (SIPP) requires special consideration due to the survey's complex design and the methodology used to adjust design weights. Balanced Repeated Replication (BRR) has proven reliable at estimating variances for a broad range of SIPP statistics, and his has been the primary method of design-based estimation since the survey began. But BRR, and replication methods in general, can be burdensome due to the amount of computing resources needed. This paper proposes a more efficient method of estimating variances using SIPP's public use files, and compares it with BRR. The alternative method uses regression residuals along with other established linearization techniques. The variances of several types of statistics will be considered, including totals, ratios, means, medians, and yearly changes. The effective degrees of freedom for each variance estimate is calculated to allow construction of confidence intervals based on the t distribution. Data from the 1996 panel of SIPP are used for numerical comparisons.

  • 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 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003