|
Activity Number:
|
519
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #303542 |
|
Title:
|
Imputation Variance Estimation by Multiple Imputation Method for the National Hospital Discharge Survey
|
|
Author(s):
|
Qiyuan Pan*+ and Iris Shimizu
|
|
Companies:
|
National Center for Health Statistics and National Center for Health Statistics
|
|
Address:
|
3311 Toledo Road, Room 3427, Hyattsville, MD, 20782,
|
|
Keywords:
|
Health care survey ; hot-deck imputation ; complex sample survey
|
|
Abstract:
|
The National Hospital Discharge Survey (NHDS) is currently conducted annually by the National Center for Health Statistics. This survey covers discharges from non-institutional, non-Federal, short-stay and general hospitals in the 50 States and the District of Columbia. Only three variables, namely age, sex and length of stay, are imputed for item non-response in NHDS data files. A hot deck method is used to impute the missing values. It is not known how this data imputation affects the variance approximations for estimates involving imputed values because the variance due to the imputation has not been evaluated for NHDS. This paper discusses an application of the multiple imputation method to estimate the magnitude of imputation variance for the 2006 NHDS.
|
