Activity Number:
|
626
- Health Policy and Real World Evidence with Administrative Data and Electronic Health Records
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 2, 2018 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Health Policy Statistics Section
|
Abstract #327208
|
Presentation
|
Title:
|
Predictive Multiple Imputation Models to Facilitate Analyzes of Association Between Contemporaneous Medicaid Enrollment Status and Health Measures Among NHANES Participants
|
Author(s):
|
Jennifer Rammon* and Jennifer Parker and Yulei He
|
Companies:
|
CDC and CDC/NCHS and CDC/NCHS
|
Keywords:
|
record linkage;
CMS;
NHANES;
multiple imputation
|
Abstract:
|
The National Health and Nutrition Examination Survey (NHANES) has been linked to the Center for Medicare and Medicaid Services' (CMS) Medicaid Enrollment and Claims Files. Linked data are produced by the National Center for Health Statistics' Data Linkage Program and are available through the NCHS Research Data Center. Assessments of the Medicaid and CHIP program rely on clear evaluations of the health of Medicaid and CHIP children. While data from currently linked files are informative, it is also of interest to evaluate more contemporaneous data. However, the linkage process takes time and delays between when survey data are released and when they are linked are unavoidable. This project assesses predictive multiple imputation models to impute Medicaid enrollment status of children for survey years that are not linked to the CMS Medicaid files. To examine the feasibility of the approach, data from 2005-2008 are used to multiply impute the Medicaid enrollment status of children from 2009-2012 and concordance rates between the actual and imputed Medicaid status are evaluated through raw frequencies and estimated associations between Medicaid enrollment and health status.
|
Authors who are presenting talks have a * after their name.