Abstract Details
Activity Number:
|
405
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract #312731
|
View Presentation
|
Title:
|
Predictive Ratio Matching Imputation of Nested Compositional Data with Semicontinuous Variables
|
Author(s):
|
Gerko Vink*+ and Jeroen Pannekoek and Stef Van Buuren
|
Companies:
|
Utrecht University and Statistics Netherlands and Utrecht University
|
Keywords:
|
Compositional data ;
Multiple Imputation ;
Predictive Ratio Matching ;
Semicontinuous data ;
Imputation ;
Restrictions
|
Abstract:
|
Imputing compositional data is challenging because imputations must obey the restrictions in the data while remaining strictly non-negative. This problem becomes increasingly complicated when the data has a nested compositional structure. We propose predictive ratio matching (PRM) as a general imputation method for compositional data. PRM imputes (nested) compositional data by iteratively updating the pairwise ratios in the data. The proposed method yields plausible inference and imputations, while keeping the intricate compositional structure, data distributions and relations intact.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.