Abstract #301532

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 2002 Program page
JSM 2002 Abstract #301532
Activity Number: 384
Type: Contributed
Date/Time: Thursday, August 15, 2002 : 8:30 AM to 10:20 AM
Sponsor: General Methodology
Abstract - #301532
Title: An Imputation Method for Data with Non-ignorable Nonresponse
Author(s): Gong Tang*+
Affiliation(s): University of Pittsburgh
Address: 307 Parran Hall, 130 DeSoto Street, Pittsburgh, Pennsylvania, 15261, US
Keywords: Missing Data ; Selection Bias ; Intermittent Missingness
Abstract:

We consider multivariate incomplete data, where missingness depends on the values of the missing variables. Standard selection models require specifying the functional form of the mechanism and maximize the full likelihood to make inference. Misspecification of the mechanism often leads to biased estimates. For multivariate monotone data, Tang, Little and Raghunathan (2001) proposed a pseudo likelihood method to estimate the complete-data model parameters without specifying the functional form of the mechanism. Based on this pseudo likelihood method, an imputation procedure is introduced to analyze general multivariate incomplete data, especially data with intermittent missingness, and its property is investigated.

  • 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 2002 program

JSM 2002

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 2002