Confidence intervals for prevalence estimates from complex surveys with imperfect assays.

There are established methods for estimating disease prevalence with associated confidence intervals for complex surveys with perfect assays, or simple random sample surveys with imperfect assays. We develop and study methods for the complicated case of complex surveys with imperfect assays. The new methods use the melding method to combine gamma intervals for directly standardized rates and established adjustments for imperfect assays by estimating sensitivity and specificity. One of the new methods appears to have at least nominal coverage in all simulated scenarios. We compare our new methods to established methods in special cases (complex surveys with perfect assays or simple surveys with imperfect assays). In some simulations, our methods appear to guarantee coverage, while competing methods have much lower than nominal coverage, especially when overall prevalence is very low. In other settings, our methods are shown to have higher than nominal coverage. We apply our method to a seroprevalence survey of SARS-CoV-2 in undiagnosed adults in the United States between May and July 2020.

Enhancing estimation methods for integrating probability and nonprobability survey samples with machine-learning techniques. An application to a Survey on the impact of the COVID-19 pandemic in Spain.

Web surveys have replaced Face-to-Face and computer assisted telephone interviewing (CATI) as the main mode of data collection in most countries. This trend was reinforced as a consequence of COVID-19 pandemic-related restrictions. However, this mode still faces significant limitations in obtaining probability-based samples of the general population. For this reason, most web surveys rely on nonprobability survey designs. Whereas probability-based designs continue to be the gold standard in survey sampling, nonprobability web surveys may still prove useful in some situations. For instance, when small subpopulations are the group under study and probability sampling is unlikely to meet sample size requirements, complementing a small probability sample with a larger nonprobability one may improve the efficiency of the estimates. Nonprobability samples may also be designed as a mean for compensating for known biases in probability-based web survey samples by purposely targeting respondent profiles that tend to be underrepresented in these surveys. This is the case in the Survey on the impact of the COVID-19 pandemic in Spain (ESPACOV) that motivates this paper. In this paper, we propose a methodology for combining probability and nonprobability web-based survey samples with the help of machine-learning techniques. We then assess the efficiency of the resulting estimates by comparing them with other strategies that have been used before. Our simulation study and the application of the proposed estimation method to the second wave of the ESPACOV Survey allow us to conclude that this is the best option for reducing the biases observed in our data.

A Multi-Site Analysis of the Prevalence of Food Insecurity in the United States, before and during the COVID-19 Pandemic.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic profoundly affected food systems including food security. Understanding how the COVID-19 pandemic impacted food security is important to provide support and identify long-term impacts and needs. OBJECTIVE: The National Food Access and COVID research Team (NFACT) was formed to assess food security over different US study sites throughout the pandemic, using common instruments and measurements. This study presents results from 18 study sites across 15 states and nationally over the first year of the COVID-19 pandemic. METHODS: A validated survey instrument was developed and implemented in whole or part through an online survey of adults across the sites throughout the first year of the pandemic, representing 22 separate surveys. Sampling methods for each study site were convenience, representative, or high-risk targeted. Food security was measured using the USDA 6-item module. Food security prevalence was analyzed using ANOVA by sampling method to assess statistically significant differences. RESULTS: Respondents (n = 27,168) indicate higher prevalence of food insecurity (low or very low food security) since the COVID-19 pandemic, compared with before the pandemic. In nearly all study sites, there is a higher prevalence of food insecurity among Black, Indigenous, and People of Color (BIPOC), households with children, and those with job disruptions. The findings demonstrate lingering food insecurity, with high prevalence over time in sites with repeat cross-sectional surveys. There are no statistically significant differences between convenience and representative surveys, but a statistically higher prevalence of food insecurity among high-risk compared with convenience surveys. CONCLUSIONS: This comprehensive study demonstrates a higher prevalence of food insecurity in the first year of the COVID-19 pandemic. These impacts were prevalent for certain demographic groups, and most pronounced for surveys targeting high-risk populations. Results especially document the continued high levels of food insecurity, as well as the variability in estimates due to the survey implementation method.