This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 348
Type: Contributed
Date/Time: Tuesday, August 3, 2010 : 10:30 AM to 12:20 PM
Sponsor: International Chinese Statistical Association
Abstract - #308106
Title: Remarks on Robust Nonparametric Imputation
Author(s): Philip E. Cheng*+
Companies: Academia Sinica
Address: 128 Academia Rd., Sec. 2, Nankang,, Taipei , 115, Taiwan
Keywords: Nearest neighbor imputation ; missing at random ; inverse weighting ; robust estimation ; kernel regression
Abstract:

Consider estimatng a population mean when responses are missing at random with a covariate variable. Two common approaches to imputing missing values are examined. The nonparametric regression approach includes the kernel regression (KR) imputation and the nearest neighbor (NN) imputation. The Horvitz-Thompson (HT) inverse weighting approach includes the basic HT imputation using kernel weights, and a nonparametric doubly robust imputation using both KR imputation and inversely weighted residuals. Asymptotic normality of the NN imputation is derived and compared to the KR imputation under standard regularity conditions of the regression function and the missing pattern function. A simulation study shows that all methods but the basic HT are robust to discontinuity of the missing data pattern, and only the NN rule using one or two neighbors is robust to mixture covariate distributions.


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 2010 program




2010 JSM Online Program Home

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.