JSM 2004 - Toronto

Abstract #300126

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); 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 2004 Program page
Activity Number: 422
Type: Invited
Date/Time: Thursday, August 12, 2004 : 10:30 AM to 12:20 PM
Sponsor: Section on Survey Research Methods
Abstract - #300126
Title: Outlier Robust Imputation of Survey Data
Author(s): Raymond Chambers and Ruilin Ren*+
Companies: University of Southampton and ORC Macro International Inc.
Address: 11785 Beltsville Drive, , MD, 20705,
Keywords: outliers ; missing data ; imputation ; robust estimation ; sample survey
Abstract:

Outlier robust methods of survey estimation, e.g., trimming, winsorization, are well known. However, such methods do not address the important practical problem of creating an "outlier free" dataset for general and public use. In particular, what is required in this situation is a dataset from which an outlier robust survey estimate can be recovered by the application of standard methods of survey estimation, such as weighting. We describe an imputation method, which we call reverse calibration, to achieve this aim. This method can be used to correct gross errors in survey data, as well as to impute missing values. We compare this method with two classical missing data imputation methods, regression imputation and nearest neighbor imputation, which we modify to accommodate outliers in the survey data. The paper concludes with an evaluation of these methods based on a realistic survey dataset.

  • 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 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004