|
Activity Number:
|
177
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 7, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #304946 |
|
Title:
|
Adjusted Jackknife for Imputation under Unequal Probability Sampling without Replacement
|
|
Author(s):
|
Yves G. Berger and Jon N. K. Rao*+
|
|
Companies:
|
Carleton University and The University of Reading
|
|
Address:
|
School of Mathematics and Statistics , Ottawa, ON, K1S 5B6, Canada
|
|
Keywords:
|
deterministic imputation ; hotdeck ; inclusion probabilities ; linearization ; pseudo-values ; random imputation
|
|
Abstract:
|
Imputation is used commonly to compensate for item nonresponse in sample surveys. If we treat the imputed values as if they are true values, and then compute the variance estimates using standard methods---such as the jackknife---we can underestimate seriously the true variances. We propose a modified jackknife variance estimator, which is defined for any without replacement of unequal probability sampling design in the presence of imputation and non-negligible sampling fraction. Mean, ratio, and random imputation methods will be considered. The practical advantage of the proposed method is its breadth of applicability.
|
