Calculating Adjusted Survival Functions for Complex Sample Survey Data and Application to Vaccination Coverage Studies with National Immunization Survey (NIS)

• Activity Number: 365
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Zhen Zhao*+ and Philip J. Smith and David Yankey and Kirk Wolter and Kennon Copeland
• Companies: CDC and CDC and CDC and NORC at the University of Chicago and NORC
• Keywords: Complex sample survey ; Adjusted survival functions ; Inverse probability weighting ; Cox corrected group adjusted ; Cumulative vaccination coverage

Abstract

In vaccination coverage studies, it is often of interest to present cumulative vaccination coverage levels using such methods as Kaplan-Meier estimates. Comparison of the estimated survival curves across subgroups may be confounded by imbalanced distribution of covariates. In general, adjusted survival functions in the context of complex sample survey design have not been described. We propose two methods to adjust the survival curves for complex sample survey data. (1)The inverse probabilities of being in a certain group are defined as the new weights and applied to obtain the inverse probability weight adjusted Kaplan-Meier survival function. (2) Survival functions are evaluated for each of the unique combination of covariate levels in a complex sample survey based on the estimated baseline cumulative hazard rate obtained from Cox proportional hazards model developed on the entire database. A weighted average of these individual survival curves is calculated with weight equal to weighted sample size of the individual curve at each of the unique covariate combination to obtain the Cox corrected group adjusted survival curve. The two proposed methods were applied to 2011 NIS data.