Estimation tools for reducing the impact of sampling and nonresponse errors in dual-frame RDD telephone surveys.

We discuss alternative estimators of the population total given a dual-frame random-digit-dial (RDD) telephone survey in which samples are selected from landline and cell phone sampling frames. The estimators are subject to sampling and nonsampling errors. To reduce sampling variability when an optimum balance of landline and cell phone samples is not feasible, we develop an application of shrinkage estimation. We demonstrate the implications for survey weighting of a differential nonresponse mechanism by telephone status. We illustrate these ideas using data from the National Immunization Survey-Child, a large dual-frame RDD telephone survey sponsored by the Centers for Disease Control and Prevention and conducted to measure the vaccination status of American children aged 19 to 35 months.

Estimating county-level vaccination coverage using small area estimation with the National Immunization Survey-Child.

The National Immunization Survey-Child (NIS-Child) provides annual vaccination coverage estimates in the United States for children aged 19 through 35 months, nationally, for each state, and for select local areas and territories. There is a need for vaccination coverage estimates for smaller geographic areas to support local authority planning and identify counties with potentially low vaccination coverage for possible further intervention. We describe small area estimation methods using 2008-2018 NIS-Child data to generate county-level estimates for children up to two years of age born 2007-2011 and 2012-2016. We applied an empirical best linear unbiased prediction method to combine direct estimates of vaccination coverage with model-based prediction using county-level predictors regarding health and demographic characteristics. We review the predictors commonly selected for the small area models and note multiple predictors related to barriers to vaccination.

Developing a sampling methodology for timely reporting of population-based COVID-19-associated hospitalization surveillance in the United States, COVID-NET 2020-2021.

BACKGROUND: The COVID-19-Associated Hospitalization Surveillance Network (COVID-NET) required a sampling methodology that allowed for production of timely population-based clinical estimates to inform the ongoing US COVID-19 pandemic response. METHODS: We developed a flexible sampling approach that considered reporting delays, differential hospitalized case burden across surveillance sites, and changing geographic and demographic trends over time. We incorporated weighting methods to adjust for the probability of selection and non-response, and to calibrate the sampled case distribution to the population distribution on demographics. We additionally developed procedures for variance estimation. RESULTS: Between March 2020 and June 2021, 19,293 (10.4%) of all adult hospitalized cases were sampled for chart abstraction. Variance estimates for select variables of interest were within desired ranges. CONCLUSIONS: COVID-NET's sampling methodology allowed for reporting of robust and timely, population-based data on the clinical epidemiology of COVID-19-associated hospitalizations and evolving trends over time, while attempting to reduce data collection burden on surveillance sites. Such methods may provide a general framework for other surveillance systems needing to quickly and efficiently collect and disseminate data for public health action.

Quantifying bias in a health survey: modeling total survey error in the national immunization survey.

Random-digit-dial telephone surveys are experiencing both declining response rates and increasing under-coverage due to the prevalence of households that substitute a wireless telephone for their residential landline telephone. These changes increase the potential for bias in survey estimates and heighten the need for survey researchers to evaluate the sources and magnitudes of potential bias. We apply a Monte Carlo simulation-based approach to assess bias in the NIS, a land-line telephone survey of 19-35 month-old children used to obtain national vaccination coverage estimates. We develop a model describing the survey stages at which component nonsampling error may be introduced due to nonresponse and under-coverage. We use that model and components of error estimated in special studies to quantify the extent to which noncoverage and nonresponse may bias the vaccination coverage estimates obtained from the NIS and present a distribution of the total survey error. Results indicated that the total error followed a normal distribution with mean of 1.72 per cent(95 per cent CI: 1.71, 1.74 per cent) and final adjusted survey weights corrected for this error. Although small, the largest contributor to error in terms of magnitude was nonresponse of immunization providers. The total error was most sensitive to declines in coverage due to cell phone only households. These results indicate that, while response rates and coverage may be declining, total survey error is quite small. Since response rates have historically been used to proxy for total survey error, the finding that these rates do not accurately reflect bias is important for evaluation of survey data. Published in 2011 by John Wiley & Sons, Ltd.

Adaptive Design in the National Immunization Survey-Teen Provider Record Check Phase.

Adaptive design principles are applied to the National Immunization Survey-Teen (NIS-Teen), sponsored by Centers for Disease Control and Prevention, which monitors vaccination coverage of U.S. adolescents age 13-17 years. Data collection is ongoing in two phases: (1) a random-digit-dial telephone survey to interview parents/guardians with age-eligible adolescents, followed by (2) a mail survey to vaccination providers, called the provider record check (PRC), to obtain vaccination histories for the adolescents. A logistic regression model relating the probability that an Immunization History Questionnaire (IHQ) is returned for a teen-provider pair to characteristics of the adolescent, mother, household, and providers was fit. R-indicators and partial R-indicators for the PRC phase of the 2015 NIS-Teen are presented to evaluate the representativeness of response in the PRC. The indicators are visualized using interactive graphics embodied in an R Shiny application to track the real time changes. Programmatic interventions to improve representativeness are discussed, which include strategies for prompting providers and special treatment of certain subgroups.

Statistical Methodology of the National Immunization Survey, 2005-2014.

The National Immunization Survey (NIS) family of surveys includes NIS-Child, which monitors vaccination coverage for the U.S. population of children aged 19-35 months; NIS- Teen, which monitors vaccination coverage for the U.S. population of adolescents aged 13-17; and NIS-Flu, which monitors influenza vaccination coverage for the U.S. population of children aged 6 months through 17 years. This report describes the methods used in this family of surveys during the 2005-2014 period.

Optimum allocation for a dual-frame telephone survey.

Careful design of a dual-frame random digit dial (RDD) telephone survey requires selecting from among many options that have varying impacts on cost, precision, and coverage in order to obtain the best possible implementation of the study goals. One such consideration is whether to screen cell-phone households in order to interview cell-phone only (CPO) households and exclude dual-user household, or to take all interviews obtained via the cell-phone sample. We present a framework in which to consider the tradeoffs between these two options and a method to select the optimal design. We derive and discuss the optimum allocation of sample size between the two sampling frames and explore the choice of optimum p, the mixing parameter for the dual-user domain. We illustrate our methods using the National Immunization Survey, sponsored by the Centers for Disease Control and Prevention.

Effect of vaccine shortages on timeliness of pneumococcal conjugate vaccination: results from the 2001-2005 National Immunization Survey.

BACKGROUND: In September 2001 and again in February 2004, the Centers for Disease Control and Prevention announced shortages in the supply of the pneumococcal conjugate vaccine. We describe the effects of the pneumococcal conjugate vaccine shortages in 2001-2003 and 2004 on the timeliness of vaccination uptake for quarterly birth cohorts affected by the shortages. METHODS: A total of 102,478 19- to 35-month-old children were sampled by the National Immunization Survey between 2001 and 2005. Provider-reported vaccination histories were used to evaluate whether children had been administered > or = 4 doses of pneumococcal conjugate vaccine by 16 months of age. RESULTS: Among successive birth cohorts affected by the first shortage, estimated coverage of > or = 4 doses of pneumococcal conjugate vaccine by 16 months declined significantly from 28.8% to 18.2%. As the first shortage ended, estimated coverage of > or = 4 doses of pneumococcal conjugate vaccine by 16 months increased steadily with each successive birth cohort to 40.2%. From the onset of the second shortage, estimated coverage of > or = 4 doses of pneumococcal conjugate vaccine by 16 months declined steadily and significantly to 13.7%. As many as 27% of parents whose child was affected by the first shortage reported that their child's vaccination provider had delayed the administration of pneumococcal conjugate vaccine doses. Of those parents who said that a pneumococcal conjugate vaccine dose was delayed and whose child was not administered > or = 4 doses, 2.9% received a reminder notice from the provider to schedule administration of those delayed doses, and 0.2% had an appointment to receive those delayed or missed doses. CONCLUSIONS: Vaccine shortages can result in delayed or missed doses and can have a dramatic impact on the vaccine coverage of children. Vaccination providers need to communicate effectively with parents so that doses that are delayed or missed during a vaccine shortage are administered when the shortage is resolved.