Online Program Home
My Program

Abstract Details

Activity Number: 661
Type: Contributed
Date/Time: Thursday, August 4, 2016 : 8:30 AM to 10:20 AM
Sponsor: Survey Research Methods Section
Abstract #319582 View Presentation
Title: Total Survey Error in a National Survey of Influenza Vaccination with Recall Error
Author(s): Nicholas Davis* and Kennon Copeland and Lin Liu and Tammy Santibanez and Jim Singleton and Zhen Zhao and David Yankey and Katherine Kahn and Yusheng Zhai and Jenny Jeyarajah
Companies: NORC at the University of Chicago and NORC at the University of Chicago and NORC at the University of Chicago and CDC and CDC and CDC and CDC/NCIRD and CDC/NCIRD and CDC/NCIRD and CDC
Keywords: Total Survey Error ; Influenza ; Vaccination ; Sampling ; Nonresponse ; Recall

Total survey error (TSE) is the difference between the estimate of an outcome derived from survey data and the outcome's true population value and reflects the total effect of sampling and nonsampling error. Using data from the National Immunization Survey (NIS) on influenza vaccination among children 6 months -17 years, this analysis considers three components of nonsampling error, or bias, due to: undercoverage of households by the sampling frame; household nonresponse; and recall error in parental reports of children's vaccination status. We estimate the distribution parameters of each source of bias and employ simulation techniques to combine nonsampling with sampling error and estimate TSE, which we define as a random variable with a statistical distribution. We approximate the distribution of total bias in estimates of influenza vaccination and quantify the extent to which each source of survey error contributes to total bias. Findings can be used to guide programmatic interpretation of NIS survey estimates and assess the sensitivity of models of the number of influenza illnesses in children prevented by vaccination due to errors in estimates of vaccination coverage.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association